Computer Vision and Pattern Recognition (cs.CV)

Abstract: Despite the significant progress in six degrees-of-freedom (6DoF) object pose estimation, existing methods have limited applicability in real-world scenarios involving embodied agents and downstream 3D vision tasks. These limitations mainly come from the necessity of 3D models, closed-category detection, and a large number of densely annotated support views. To mitigate this issue, we propose a general paradigm for object pose estimation, called Promptable Object Pose Estimation (POPE). The proposed approach POPE enables zero-shot 6DoF object pose estimation for any target object in any scene, while only a single reference is adopted as the support view. To achieve this, POPE leverages the power of the pre-trained large-scale 2D foundation model, employs a framework with hierarchical feature representation and 3D geometry principles. Moreover, it estimates the relative camera pose between object prompts and the target object in new views, enabling both two-view and multi-view 6DoF pose estimation tasks. Comprehensive experimental results demonstrate that POPE exhibits unrivaled robust performance in zero-shot settings, by achieving a significant reduction in the averaged Median Pose Error by 52.38% and 50.47% on the LINEMOD and OnePose datasets, respectively. We also conduct more challenging testings in causally captured images (see Figure 1), which further demonstrates the robustness of POPE. Project page can be found with https://paulpanwang.github.io/POPE/.

Abstract: In this paper, we propose a novel language-guided 3D arbitrary neural style transfer method (CLIP3Dstyler). We aim at stylizing any 3D scene with an arbitrary style from a text description, and synthesizing the novel stylized view, which is more flexible than the image-conditioned style transfer. Compared with the previous 2D method CLIPStyler, we are able to stylize a 3D scene and generalize to novel scenes without re-train our model. A straightforward solution is to combine previous image-conditioned 3D style transfer and text-conditioned 2D style transfer \bigskip methods. However, such a solution cannot achieve our goal due to two main challenges. First, there is no multi-modal model matching point clouds and language at different feature scales (low-level, high-level). Second, we observe a style mixing issue when we stylize the content with different style conditions from text prompts. To address the first issue, we propose a 3D stylization framework to match the point cloud features with text features in local and global views. For the second issue, we propose an improved directional divergence loss to make arbitrary text styles more distinguishable as a complement to our framework. We conduct extensive experiments to show the effectiveness of our model on text-guided 3D scene style transfer.

Abstract: When virtual agents interact with humans, gestures are crucial to delivering their intentions with speech. Previous multimodal co-speech gesture generation models required encoded features of all modalities to generate gestures. If some input modalities are removed or contain noise, the model may not generate the gestures properly. To acquire robust and generalized encodings, we propose a novel framework with a multimodal pre-trained encoder for co-speech gesture generation. In the proposed method, the multi-head-attention-based encoder is trained with self-supervised learning to contain the information on each modality. Moreover, we collect full-body gestures that consist of 3D joint rotations to improve visualization and apply gestures to the extensible body model. Through the series of experiments and human evaluation, the proposed method renders realistic co-speech gestures not only when all input modalities are given but also when the input modalities are missing or noisy.

Abstract: In dyadic interaction, predicting the listener's facial reactions is challenging as different reactions may be appropriate in response to the same speaker's behaviour. This paper presents a novel framework called ReactFace that learns an appropriate facial reaction distribution from a speaker's behaviour rather than replicating the real facial reaction of the listener. ReactFace generates multiple different but appropriate photo-realistic human facial reactions by (i) learning an appropriate facial reaction distribution representing multiple appropriate facial reactions; and (ii) synchronizing the generated facial reactions with the speaker's verbal and non-verbal behaviours at each time stamp, resulting in realistic 2D facial reaction sequences. Experimental results demonstrate the effectiveness of our approach in generating multiple diverse, synchronized, and appropriate facial reactions from each speaker's behaviour, with the quality of the generated reactions being influenced by the speaker's speech and facial behaviours. Our code is made publicly available at \url{https://github.com/lingjivoo/ReactFace}.

Abstract: In recent years, 3D models have been utilized in many applications, such as auto-driver, 3D reconstruction, VR, and AR. However, the scarcity of 3D model data does not meet its practical demands. Thus, generating high-quality 3D models efficiently from textual descriptions is a promising but challenging way to solve this problem. In this paper, inspired by the ability of human beings to complement visual information details from ambiguous descriptions based on their own experience, we propose a novel text-3D generation model (T2TD), which introduces the related shapes or textual information as the prior knowledge to improve the performance of the 3D generation model. In this process, we first introduce the text-3D knowledge graph to save the relationship between 3D models and textual semantic information, which can provide the related shapes to guide the target 3D model generation. Second, we integrate an effective causal inference model to select useful feature information from these related shapes, which removes the unrelated shape information and only maintains feature information that is strongly relevant to the textual description. Meanwhile, to effectively integrate multi-modal prior knowledge into textual information, we adopt a novel multi-layer transformer structure to progressively fuse related shape and textual information, which can effectively compensate for the lack of structural information in the text and enhance the final performance of the 3D generation model. The final experimental results demonstrate that our approach significantly improves 3D model generation quality and outperforms the SOTA methods on the text2shape datasets.

Abstract: Many existing multi-modality studies are based on the assumption of modality integrity. However, the problem of missing arbitrary modalities is very common in real life, and this problem is less studied, but actually important in the task of multi-modality person re-identification (Re-ID). To this end, we design a novel dynamic enhancement network (DENet), which allows missing arbitrary modalities while maintaining the representation ability of multiple modalities, for partial multi-modality person Re-ID. To be specific, the multi-modal representation of the RGB, near-infrared (NIR) and thermal-infrared (TIR) images is learned by three branches, in which the information of missing modalities is recovered by the feature transformation module. Since the missing state might be changeable, we design a dynamic enhancement module, which dynamically enhances modality features according to the missing state in an adaptive manner, to improve the multi-modality representation. Extensive experiments on multi-modality person Re-ID dataset RGBNT201 and vehicle Re-ID dataset RGBNT100 comparing to the state-of-the-art methods verify the effectiveness of our method in complex and changeable environments.

Abstract: Existing vehicle re-identification methods mainly rely on the single query, which has limited information for vehicle representation and thus significantly hinders the performance of vehicle Re-ID in complicated surveillance networks. In this paper, we propose a more realistic and easily accessible task, called multi-query vehicle Re-ID, which leverages multiple queries to overcome viewpoint limitation of single one. Based on this task, we make three major contributions. First, we design a novel viewpoint-conditioned network (VCNet), which adaptively combines the complementary information from different vehicle viewpoints, for multi-query vehicle Re-ID. Moreover, to deal with the problem of missing vehicle viewpoints, we propose a cross-view feature recovery module which recovers the features of the missing viewpoints by learnt the correlation between the features of available and missing viewpoints. Second, we create a unified benchmark dataset, taken by 6142 cameras from a real-life transportation surveillance system, with comprehensive viewpoints and large number of crossed scenes of each vehicle for multi-query vehicle Re-ID evaluation. Finally, we design a new evaluation metric, called mean cross-scene precision (mCSP), which measures the ability of cross-scene recognition by suppressing the positive samples with similar viewpoints from same camera. Comprehensive experiments validate the superiority of the proposed method against other methods, as well as the effectiveness of the designed metric in the evaluation of multi-query vehicle Re-ID.

Abstract: This paper addresses the problem of 3D referring expression comprehension (REC) in autonomous driving scenario, which aims to ground a natural language to the targeted region in LiDAR point clouds. Previous approaches for REC usually focus on the 2D or 3D-indoor domain, which is not suitable for accurately predicting the location of the queried 3D region in an autonomous driving scene. In addition, the upper-bound limitation and the heavy computation cost motivate us to explore a better solution. In this work, we propose a new multi-modal visual grounding task, termed LiDAR Grounding. Then we devise a Multi-modal Single Shot Grounding (MSSG) approach with an effective token fusion strategy. It jointly learns the LiDAR-based object detector with the language features and predicts the targeted region directly from the detector without any post-processing. Moreover, the image feature can be flexibly integrated into our approach to provide rich texture and color information. The cross-modal learning enforces the detector to concentrate on important regions in the point cloud by considering the informative language expressions, thus leading to much better accuracy and efficiency. Extensive experiments on the Talk2Car dataset demonstrate the effectiveness of the proposed methods. Our work offers a deeper insight into the LiDAR-based grounding task and we expect it presents a promising direction for the autonomous driving community.

Abstract: Recent developments in the field of non-local attention (NLA) have led to a renewed interest in self-similarity-based single image super-resolution (SISR). Researchers usually used the NLA to explore non-local self-similarity (NSS) in SISR and achieve satisfactory reconstruction results. However, a surprising phenomenon that the reconstruction performance of the standard NLA is similar to the NLA with randomly selected regions stimulated our interest to revisit NLA. In this paper, we first analyzed the attention map of the standard NLA from different perspectives and discovered that the resulting probability distribution always has full support for every local feature, which implies a statistical waste of assigning values to irrelevant non-local features, especially for SISR which needs to model long-range dependence with a large number of redundant non-local features. Based on these findings, we introduced a concise yet effective soft thresholding operation to obtain high-similarity-pass attention (HSPA), which is beneficial for generating a more compact and interpretable distribution. Furthermore, we derived some key properties of the soft thresholding operation that enable training our HSPA in an end-to-end manner. The HSPA can be integrated into existing deep SISR models as an efficient general building block. In addition, to demonstrate the effectiveness of the HSPA, we constructed a deep high-similarity-pass attention network (HSPAN) by integrating a few HSPAs in a simple backbone. Extensive experimental results demonstrate that HSPAN outperforms state-of-the-art approaches on both quantitative and qualitative evaluations.

Abstract: The multi-scale information among the whole slide images (WSIs) is essential for cancer diagnosis. Although the existing multi-scale vision Transformer has shown its effectiveness for learning multi-scale image representation, it still cannot work well on the gigapixel WSIs due to their extremely large image sizes. To this end, we propose a novel Multi-scale Efficient Graph-Transformer (MEGT) framework for WSI classification. The key idea of MEGT is to adopt two independent Efficient Graph-based Transformer (EGT) branches to process the low-resolution and high-resolution patch embeddings (i.e., tokens in a Transformer) of WSIs, respectively, and then fuse these tokens via a multi-scale feature fusion module (MFFM). Specifically, we design an EGT to efficiently learn the local-global information of patch tokens, which integrates the graph representation into Transformer to capture spatial-related information of WSIs. Meanwhile, we propose a novel MFFM to alleviate the semantic gap among different resolution patches during feature fusion, which creates a non-patch token for each branch as an agent to exchange information with another branch by cross-attention. In addition, to expedite network training, a novel token pruning module is developed in EGT to reduce the redundant tokens. Extensive experiments on TCGA-RCC and CAMELYON16 datasets demonstrate the effectiveness of the proposed MEGT.

Abstract: Text-to-image diffusion models can generate diverse, high-fidelity images based on user-provided text prompts. Recent research has extended these models to support text-guided image editing. While text guidance is an intuitive editing interface for users, it often fails to ensure the precise concept conveyed by users. To address this issue, we propose Custom-Edit, in which we (i) customize a diffusion model with a few reference images and then (ii) perform text-guided editing. Our key discovery is that customizing only language-relevant parameters with augmented prompts improves reference similarity significantly while maintaining source similarity. Moreover, we provide our recipe for each customization and editing process. We compare popular customization methods and validate our findings on two editing methods using various datasets.

Abstract: The tremendous success of large models trained on extensive datasets demonstrates that scale is a key ingredient in achieving superior results. Therefore, the reflection on the rationality of designing knowledge distillation (KD) approaches for limited-capacity architectures solely based on small-scale datasets is now deemed imperative. In this paper, we identify the \emph{small data pitfall} that presents in previous KD methods, which results in the underestimation of the power of vanilla KD framework on large-scale datasets such as ImageNet-1K. Specifically, we show that employing stronger data augmentation techniques and using larger datasets can directly decrease the gap between vanilla KD and other meticulously designed KD variants. This highlights the necessity of designing and evaluating KD approaches in the context of practical scenarios, casting off the limitations of small-scale datasets. Our investigation of the vanilla KD and its variants in more complex schemes, including stronger training strategies and different model capacities, demonstrates that vanilla KD is elegantly simple but astonishingly effective in large-scale scenarios. Without bells and whistles, we obtain state-of-the-art ResNet-50, ViT-S, and ConvNeXtV2-T models for ImageNet, which achieve 83.1\%, 84.3\%, and 85.0\% top-1 accuracy, respectively. PyTorch code and checkpoints can be found at https://github.com/Hao840/vanillaKD.

Abstract: Generating and editing a 3D scene guided by natural language poses a challenge, primarily due to the complexity of specifying the positional relations and volumetric changes within the 3D space. Recent advancements in Large Language Models (LLMs) have demonstrated impressive reasoning, conversational, and zero-shot generation abilities across various domains. Surprisingly, these models also show great potential in realizing and interpreting the 3D space. In light of this, we propose a novel language-guided interactive 3D generation system, dubbed LI3D, that integrates LLMs as a 3D layout interpreter into the off-the-shelf layout-to-3D generative models, allowing users to flexibly and interactively generate visual content. Specifically, we design a versatile layout structure base on the bounding boxes and semantics to prompt the LLMs to model the spatial generation and reasoning from language. Our system also incorporates LLaVA, a large language and vision assistant, to provide generative feedback from the visual aspect for improving the visual quality of generated content. We validate the effectiveness of LI3D, primarily in 3D generation and editing through multi-round interactions, which can be flexibly extended to 2D generation and editing. Various experiments demonstrate the potential benefits of incorporating LLMs in generative AI for applications, e.g., metaverse. Moreover, we benchmark the layout reasoning performance of LLMs with neural visual artist tasks, revealing their emergent ability in the spatial layout domain.

Abstract: Pseudo-labels are widely employed in weakly supervised 3D segmentation tasks where only sparse ground-truth labels are available for learning. Existing methods often rely on empirical label selection strategies, such as confidence thresholding, to generate beneficial pseudo-labels for model training. This approach may, however, hinder the comprehensive exploitation of unlabeled data points. We hypothesize that this selective usage arises from the noise in pseudo-labels generated on unlabeled data. The noise in pseudo-labels may result in significant discrepancies between pseudo-labels and model predictions, thus confusing and affecting the model training greatly. To address this issue, we propose a novel learning strategy to regularize the generated pseudo-labels and effectively narrow the gaps between pseudo-labels and model predictions. More specifically, our method introduces an Entropy Regularization loss and a Distribution Alignment loss for weakly supervised learning in 3D segmentation tasks, resulting in an ERDA learning strategy. Interestingly, by using KL distance to formulate the distribution alignment loss, it reduces to a deceptively simple cross-entropy-based loss which optimizes both the pseudo-label generation network and the 3D segmentation network simultaneously. Despite the simplicity, our method promisingly improves the performance. We validate the effectiveness through extensive experiments on various baselines and large-scale datasets. Results show that ERDA effectively enables the effective usage of all unlabeled data points for learning and achieves state-of-the-art performance under different settings. Remarkably, our method can outperform fully-supervised baselines using only 1% of true annotations. Code and model will be made publicly available.

Abstract: Architectures that first convert point clouds to a grid representation and then apply convolutional neural networks achieve good performance for radar-based object detection. However, the transfer from irregular point cloud data to a dense grid structure is often associated with a loss of information, due to the discretization and aggregation of points. In this paper, we propose a novel architecture, multi-scale KPPillarsBEV, that aims to mitigate the negative effects of grid rendering. Specifically, we propose a novel grid rendering method, KPBEV, which leverages the descriptive power of kernel point convolutions to improve the encoding of local point cloud contexts during grid rendering. In addition, we propose a general multi-scale grid rendering formulation to incorporate multi-scale feature maps into convolutional backbones of detection networks with arbitrary grid rendering methods. We perform extensive experiments on the nuScenes dataset and evaluate the methods in terms of detection performance and computational complexity. The proposed multi-scale KPPillarsBEV architecture outperforms the baseline by 5.37% and the previous state of the art by 2.88% in Car AP4.0 (average precision for a matching threshold of 4 meters) on the nuScenes validation set. Moreover, the proposed single-scale KPBEV grid rendering improves the Car AP4.0 by 2.90% over the baseline while maintaining the same inference speed.

Abstract: Due to recent advances in pose-estimation methods, human motion can be extracted from a common video in the form of 3D skeleton sequences. Despite wonderful application opportunities, effective and efficient content-based access to large volumes of such spatio-temporal skeleton data still remains a challenging problem. In this paper, we propose a novel content-based text-to-motion retrieval task, which aims at retrieving relevant motions based on a specified natural-language textual description. To define baselines for this uncharted task, we employ the BERT and CLIP language representations to encode the text modality and successful spatio-temporal models to encode the motion modality. We additionally introduce our transformer-based approach, called Motion Transformer (MoT), which employs divided space-time attention to effectively aggregate the different skeleton joints in space and time. Inspired by the recent progress in text-to-image/video matching, we experiment with two widely-adopted metric-learning loss functions. Finally, we set up a common evaluation protocol by defining qualitative metrics for assessing the quality of the retrieved motions, targeting the two recently-introduced KIT Motion-Language and HumanML3D datasets. The code for reproducing our results is available at https://github.com/mesnico/text-to-motion-retrieval.

Abstract: Image fusion plays a key role in a variety of multi-sensor-based vision systems, especially for enhancing visual quality and/or extracting aggregated features for perception. However, most existing methods just consider image fusion as an individual task, thus ignoring its underlying relationship with these downstream vision problems. Furthermore, designing proper fusion architectures often requires huge engineering labor. It also lacks mechanisms to improve the flexibility and generalization ability of current fusion approaches. To mitigate these issues, we establish a Task-guided, Implicit-searched and Meta-initialized (TIM) deep model to address the image fusion problem in a challenging real-world scenario. Specifically, we first propose a constrained strategy to incorporate information from downstream tasks to guide the unsupervised learning process of image fusion. Within this framework, we then design an implicit search scheme to automatically discover compact architectures for our fusion model with high efficiency. In addition, a pretext meta initialization technique is introduced to leverage divergence fusion data to support fast adaptation for different kinds of image fusion tasks. Qualitative and quantitative experimental results on different categories of image fusion problems and related downstream tasks (e.g., visual enhancement and semantic understanding) substantiate the flexibility and effectiveness of our TIM. The source code will be available at https://github.com/LiuZhu-CV/TIMFusion.

Abstract: Addressing accuracy limitations and pose ambiguity in 6D object pose estimation from single RGB images presents a significant challenge, particularly due to object symmetries or occlusions. In response, we introduce a novel score-based diffusion method applied to the $SE(3)$ group, marking the first application of diffusion models to $SE(3)$ within the image domain, specifically tailored for pose estimation tasks. Extensive evaluations demonstrate the method's efficacy in handling pose ambiguity, mitigating perspective-induced ambiguity, and showcasing the robustness of our surrogate Stein score formulation on $SE(3)$. This formulation not only improves the convergence of Langevin dynamics but also enhances computational efficiency. Thus, we pioneer a promising strategy for 6D object pose estimation.

Abstract: Radars and cameras belong to the most frequently used sensors for advanced driver assistance systems and automated driving research. However, there has been surprisingly little research on radar-camera fusion with neural networks. One of the reasons is a lack of large-scale automotive datasets with radar and unmasked camera data, with the exception of the nuScenes dataset. Another reason is the difficulty of effectively fusing the sparse radar point cloud on the bird's eye view (BEV) plane with the dense images on the perspective plane. The recent trend of camera-based 3D object detection using BEV features has enabled a new type of fusion, which is better suited for radars. In this work, we present RC-BEVFusion, a modular radar-camera fusion network on the BEV plane. We propose BEVFeatureNet, a novel radar encoder branch, and show that it can be incorporated into several state-of-the-art camera-based architectures. We show significant performance gains of up to 28% increase in the nuScenes detection score, which is an important step in radar-camera fusion research. Without tuning our model for the nuScenes benchmark, we achieve the best result among all published methods in the radar-camera fusion category.

Abstract: Transformer-based trackers have achieved strong accuracy on the standard benchmarks. However, their efficiency remains an obstacle to practical deployment on both GPU and CPU platforms. In this paper, to overcome this issue, we propose a fully transformer tracking framework, coined as \emph{MixFormerV2}, without any dense convolutional operation and complex score prediction module. Our key design is to introduce four special prediction tokens and concatenate them with the tokens from target template and search areas. Then, we apply the unified transformer backbone on these mixed token sequence. These prediction tokens are able to capture the complex correlation between target template and search area via mixed attentions. Based on them, we can easily predict the tracking box and estimate its confidence score through simple MLP heads. To further improve the efficiency of MixFormerV2, we present a new distillation-based model reduction paradigm, including dense-to-sparse distillation and deep-to-shallow distillation. The former one aims to transfer knowledge from the dense-head based MixViT to our fully transformer tracker, while the latter one is used to prune some layers of the backbone. We instantiate two types of MixForemrV2, where the MixFormerV2-B achieves an AUC of 70.6\% on LaSOT and an AUC of 57.4\% on TNL2k with a high GPU speed of 165 FPS, and the MixFormerV2-S surpasses FEAR-L by 2.7\% AUC on LaSOT with a real-time CPU speed.

Abstract: Object Re-identification (ReID) aims to retrieve the probe object from many gallery images with the ReID model inferred based on a stationary camera-free dataset by associating and collecting the identities across all camera views. When deploying the ReID algorithm in real-world scenarios, the aspect of storage, privacy constraints, and dynamic changes of cameras would degrade its generalizability and applicability. Treating each camera's data independently, we introduce a novel ReID task named Camera-Incremental Object Re-identification (CIOR) by continually optimizing the ReID mode from the incoming stream of the camera dataset. Since the identities under different camera views might describe the same object, associating and distilling the knowledge of common identities would boost the discrimination and benefit from alleviating the catastrophic forgetting. In this paper, we propose a novel Identity Knowledge Evolution (IKE) framework for CIOR, consisting of the Identity Knowledge Association (IKA), Identity Knowledge Distillation (IKD), and Identity Knowledge Update (IKU). IKA is proposed to discover the common identities between the current identity and historical identities. IKD has applied to distillate historical identity knowledge from common identities and quickly adapt the historical model to the current camera view. After each camera has been trained, IKU is applied to continually expand the identity knowledge by combining the historical and current identity memories. The evaluation of Market-CL and Veri-CL shows the Identity Knowledge Evolution (IKE) effectiveness for CIOR. code:https://github.com/htyao89/Camera-Incremental-Object-ReID

Abstract: Detecting 3D mask attacks to a face recognition system is challenging. Although genuine faces and 3D face masks show significantly different remote photoplethysmography (rPPG) signals, rPPG-based face anti-spoofing methods often suffer from performance degradation due to unstable face alignment in the video sequence and weak rPPG signals. To enhance the rPPG signal in a motion-robust way, a landmark-anchored face stitching method is proposed to align the faces robustly and precisely at the pixel-wise level by using both SIFT keypoints and facial landmarks. To better encode the rPPG signal, a weighted spatial-temporal representation is proposed, which emphasizes the face regions with rich blood vessels. In addition, characteristics of rPPG signals in different color spaces are jointly utilized. To improve the generalization capability, a lightweight EfficientNet with a Gated Recurrent Unit (GRU) is designed to extract both spatial and temporal features from the rPPG spatial-temporal representation for classification. The proposed method is compared with the state-of-the-art methods on five benchmark datasets under both intra-dataset and cross-dataset evaluations. The proposed method shows a significant and consistent improvement in performance over other state-of-the-art rPPG-based methods for face spoofing detection.

Abstract: The ability to anticipate pedestrian motion changes is a critical capability for autonomous vehicles. In urban environments, pedestrians may enter the road area and create a high risk for driving, and it is important to identify these cases. Typical predictors use the trajectory history to predict future motion, however in cases of motion initiation, motion in the trajectory may only be clearly visible after a delay, which can result in the pedestrian has entered the road area before an accurate prediction can be made. Appearance data includes useful information such as changes of gait, which are early indicators of motion changes, and can inform trajectory prediction. This work presents a comparative evaluation of trajectory-only and appearance-based methods for pedestrian prediction, and introduces a new dataset experiment for prediction using appearance. We create two trajectory and image datasets based on the combination of image and trajectory sequences from the popular NuScenes dataset, and examine prediction of trajectories using observed appearance to influence futures. This shows some advantages over trajectory prediction alone, although problems with the dataset prevent advantages of appearance-based models from being shown. We describe methods for improving the dataset and experiment to allow benefits of appearance-based models to be captured.

Abstract: Reconstruction-based methods have struggled to achieve competitive performance on anomaly detection. In this paper, we introduce Denoising Diffusion Anomaly Detection (DDAD). We propose a novel denoising process for image reconstruction conditioned on a target image. This results in a coherent restoration that closely resembles the target image. Subsequently, our anomaly detection framework leverages this conditioning where the target image is set as the input image to guide the denoising process, leading to defectless reconstruction while maintaining nominal patterns. We localise anomalies via a pixel-wise and feature-wise comparison of the input and reconstructed image. Finally, to enhance the effectiveness of feature comparison, we introduce a domain adaptation method that utilises generated examples from our conditioned denoising process to fine-tune the feature extractor. The veracity of the approach is demonstrated on various datasets including MVTec and VisA benchmarks, achieving state-of-the-art results of 99.5% and 99.3% image-level AUROC respectively.

Abstract: Large pre-trained models have had a significant impact on computer vision by enabling multi-modal learning, where the CLIP model has achieved impressive results in image classification, object detection, and semantic segmentation. However, the model's performance on 3D point cloud processing tasks is limited due to the domain gap between depth maps from 3D projection and training images of CLIP. This paper proposes DiffCLIP, a new pre-training framework that incorporates stable diffusion with ControlNet to minimize the domain gap in the visual branch. Additionally, a style-prompt generation module is introduced for few-shot tasks in the textual branch. Extensive experiments on the ModelNet10, ModelNet40, and ScanObjectNN datasets show that DiffCLIP has strong abilities for 3D understanding. By using stable diffusion and style-prompt generation, DiffCLIP achieves an accuracy of 43.2\% for zero-shot classification on OBJ\_BG of ScanObjectNN, which is state-of-the-art performance, and an accuracy of 80.6\% for zero-shot classification on ModelNet10, which is comparable to state-of-the-art performance.

Abstract: The potential of integrating Computer-Assisted Diagnosis (CAD) with Large Language Models (LLMs) in clinical applications, particularly in digital family doctor and clinic assistant roles, shows promise. However, existing works have limitations in terms of reliability, effectiveness, and their narrow applicability to specific image domains, which restricts their overall processing capabilities. Moreover, the mismatch in writing style between LLMs and radiologists undermines their practical utility. To address these challenges, we present ChatCAD+, an interactive CAD system that is universal, reliable, and capable of handling medical images from diverse domains. ChatCAD+ utilizes current information obtained from reputable medical websites to offer precise medical advice. Additionally, it incorporates a template retrieval system that emulates real-world diagnostic reporting, thereby improving its seamless integration into existing clinical workflows. The source code is available at https://github.com/zhaozh10/ChatCAD. The online demo will be available soon.

Abstract: In order to deploy automated vehicles to the public, it has to be proven that the vehicle can safely and robustly handle traffic in many different scenarios. One important component of automated vehicles is the perception system that captures and processes the environment around the vehicle. Perception systems require large datasets for training their deep neural network. Knowing which parts of the data in these datasets describe a corner case is an advantage during training or testing of the network. These corner cases describe situations that are rare and potentially challenging for the network. We propose a pipeline that converts collective expert knowledge descriptions into the extended KI Absicherung ontology. The ontology is used to describe scenes and scenarios that can be mapped to perception datasets. The corner cases can then be extracted from the datasets. In addition, the pipeline enables the evaluation of the detection networks against the extracted corner cases to measure their performance.

Abstract: In Knowledge Distillation, the teacher is generally much larger than the student, making the solution of the teacher likely to be difficult for the student to learn. To ease the mimicking difficulty, we introduce a triplet knowledge distillation mechanism named TriKD. Besides teacher and student, TriKD employs a third role called anchor model. Before distillation begins, the pre-trained anchor model delimits a subspace within the full solution space of the target problem. Solutions within the subspace are expected to be easy targets that the student could mimic well. Distillation then begins in an online manner, and the teacher is only allowed to express solutions within the aforementioned subspace. Surprisingly, benefiting from accurate but easy-to-mimic hints, the student can finally perform well. After the student is well trained, it can be used as the new anchor for new students, forming a curriculum learning strategy. Our experiments on image classification and face recognition with various models clearly demonstrate the effectiveness of our method. Furthermore, the proposed TriKD is also effective in dealing with the overfitting issue. Moreover, our theoretical analysis supports the rationality of our triplet distillation.

Abstract: In theory, vector quantization (VQ) is always better than scalar quantization (SQ) in terms of rate-distortion (R-D) performance. Recent state-of-the-art methods for neural image compression are mainly based on nonlinear transform coding (NTC) with uniform scalar quantization, overlooking the benefits of VQ due to its exponentially increased complexity. In this paper, we first investigate on some toy sources, demonstrating that even if modern neural networks considerably enhance the compression performance of SQ with nonlinear transform, there is still an insurmountable chasm between SQ and VQ. Therefore, revolving around VQ, we propose a novel framework for neural image compression named Nonlinear Vector Transform Coding (NVTC). NVTC solves the critical complexity issue of VQ through (1) a multi-stage quantization strategy and (2) nonlinear vector transforms. In addition, we apply entropy-constrained VQ in latent space to adaptively determine the quantization boundaries for joint rate-distortion optimization, which improves the performance both theoretically and experimentally. Compared to previous NTC approaches, NVTC demonstrates superior rate-distortion performance, faster decoding speed, and smaller model size. Our code is available at https://github.com/USTC-IMCL/NVTC

Abstract: Blurry images usually exhibit similar blur at various locations across the image domain, a property barely captured in nowadays blind deblurring neural networks. We show that when extracting patches of similar underlying blur is possible, jointly processing the stack of patches yields superior accuracy than handling them separately. Our collaborative scheme is implemented in a neural architecture with a pooling layer on the stack dimension. We present three practical patch extraction strategies for image sharpening, camera shake removal and optical aberration correction, and validate the proposed approach on both synthetic and real-world benchmarks. For each blur instance, the proposed collaborative strategy yields significant quantitative and qualitative improvements.

Abstract: Generative modeling has experienced substantial progress in recent years, particularly in text-to-image and text-to-video synthesis. However, the medical field has not yet fully exploited the potential of large-scale foundational models for synthetic data generation. In this paper, we introduce GenerateCT, the first method for text-conditional computed tomography (CT) generation, addressing the limitations in 3D medical imaging research and making our entire framework open-source. GenerateCT consists of a pre-trained large language model, a transformer-based text-conditional 3D chest CT generation architecture, and a text-conditional spatial super-resolution diffusion model. We also propose CT-ViT, which efficiently compresses CT volumes while preserving auto-regressiveness in-depth, enabling the generation of 3D CT volumes with variable numbers of axial slices. Our experiments demonstrate that GenerateCT can produce realistic, high-resolution, and high-fidelity 3D chest CT volumes consistent with medical language text prompts. We further investigate the potential of GenerateCT by training a model using generated CT volumes for multi-abnormality classification of chest CT volumes. Our contributions provide a valuable foundation for future research in text-conditional 3D medical image generation and have the potential to accelerate advancements in medical imaging research. Our code, pre-trained models, and generated data are available at https://github.com/ibrahimethemhamamci/GenerateCT.

Abstract: Audio-visual person recognition (AVPR) has received extensive attention. However, most datasets used for AVPR research so far are collected in constrained environments, and thus cannot reflect the true performance of AVPR systems in real-world scenarios. To meet the request for research on AVPR in unconstrained conditions, this paper presents a multi-genre AVPR dataset collected `in the wild', named CN-Celeb-AV. This dataset contains more than 420k video segments from 1,136 persons from public media. In particular, we put more emphasis on two real-world complexities: (1) data in multiple genres; (2) segments with partial information. A comprehensive study was conducted to compare CN-Celeb-AV with two popular public AVPR benchmark datasets, and the results demonstrated that CN-Celeb-AV is more in line with real-world scenarios and can be regarded as a new benchmark dataset for AVPR research. The dataset also involves a development set that can be used to boost the performance of AVPR systems in real-life situations. The dataset is free for researchers and can be downloaded from http://cnceleb.org/.

Abstract: In this technical report, we describe the Guided-Attention mechanism based solution for the short-term anticipation (STA) challenge for the EGO4D challenge. It combines the object detections, and the spatiotemporal features extracted from video clips, enhancing the motion and contextual information, and further decoding the object-centric and motion-centric information to address the problem of STA in egocentric videos. For the challenge, we build our model on top of StillFast with Guided Attention applied on fast network. Our model obtains better performance on the validation set and also achieves state-of-the-art (SOTA) results on the challenge test set for EGO4D Short-Term Object Interaction Anticipation Challenge.

Abstract: Building general-purpose models that can perceive diverse real-world modalities and solve various tasks is an appealing target in artificial intelligence. In this paper, we present ChatBridge, a novel multimodal language model that leverages the expressive capabilities of language as the catalyst to bridge the gap between various modalities. We show that only language-paired two-modality data is sufficient to connect all modalities. ChatBridge leverages recent large language models (LLM) and extends their zero-shot capabilities to incorporate diverse multimodal inputs. ChatBridge undergoes a two-stage training. The first stage aligns each modality with language, which brings emergent multimodal correlation and collaboration abilities. The second stage instruction-finetunes ChatBridge to align it with user intent with our newly proposed multimodal instruction tuning dataset, named MULTIS, which covers a wide range of 16 multimodal tasks of text, image, video, and audio modalities. We show strong quantitative and qualitative results on zero-shot multimodal tasks covering text, image, video, and audio modalities. All codes, data, and models of ChatBridge will be open-sourced.

Abstract: Obtaining accurate 3D object poses is vital for numerous computer vision applications, such as 3D reconstruction and scene understanding. However, annotating real-world objects is time-consuming and challenging. While synthetically generated training data is a viable alternative, the domain shift between real and synthetic data is a significant challenge. In this work, we aim to narrow the performance gap between models trained on synthetic data and few real images and fully supervised models trained on large-scale data. We achieve this by approaching the problem from two perspectives: 1) We introduce SyntheticP3D, a new synthetic dataset for object pose estimation generated from CAD models and enhanced with a novel algorithm. 2) We propose a novel approach (CC3D) for training neural mesh models that perform pose estimation via inverse rendering. In particular, we exploit the spatial relationships between features on the mesh surface and a contrastive learning scheme to guide the domain adaptation process. Combined, these two approaches enable our models to perform competitively with state-of-the-art models using only 10% of the respective real training images, while outperforming the SOTA model by 10.4% with a threshold of pi/18 using only 50% of the real training data. Our trained model further demonstrates robust generalization to out-of-distribution scenarios despite being trained with minimal real data.

Abstract: Autonomous vehicles rely on LiDAR sensors to perceive the environment. Adverse weather conditions like rain, snow, and fog negatively affect these sensors, reducing their reliability by introducing unwanted noise in the measurements. In this work, we tackle this problem by proposing a novel approach for detecting adverse weather effects in LiDAR data. We reformulate this problem as an outlier detection task and use an energy-based framework to detect outliers in point clouds. More specifically, our method learns to associate low energy scores with inlier points and high energy scores with outliers allowing for robust detection of adverse weather effects. In extensive experiments, we show that our method performs better in adverse weather detection and has higher robustness to unseen weather effects than previous state-of-the-art methods. Furthermore, we show how our method can be used to perform simultaneous outlier detection and semantic segmentation. Finally, to help expand the research field of LiDAR perception in adverse weather, we release the SemanticSpray dataset, which contains labeled vehicle spray data in highway-like scenarios. The dataset is available at http://dx.doi.org/10.18725/OPARU-48815 .

Abstract: Semantic occupancy prediction aims to infer dense geometry and semantics of surroundings for an autonomous agent to operate safely in the 3D environment. Existing occupancy prediction methods are almost entirely trained on human-annotated volumetric data. Although of high quality, the generation of such 3D annotations is laborious and costly, restricting them to a few specific object categories in the training dataset. To address this limitation, this paper proposes Open Vocabulary Occupancy (OVO), a novel approach that allows semantic occupancy prediction of arbitrary classes but without the need for 3D annotations during training. Keys to our approach are (1) knowledge distillation from a pre-trained 2D open-vocabulary segmentation model to the 3D occupancy network, and (2) pixel-voxel filtering for high-quality training data generation. The resulting framework is simple, compact, and compatible with most state-of-the-art semantic occupancy prediction models. On NYUv2 and SemanticKITTI datasets, OVO achieves competitive performance compared to supervised semantic occupancy prediction approaches. Furthermore, we conduct extensive analyses and ablation studies to offer insights into the design of the proposed framework.

Abstract: Face swapping combines one face's identity with another face's non-appearance attributes (expression, head pose, lighting) to generate a synthetic face. This technology is rapidly improving, but falls flat when reconstructing some attributes, particularly gaze. Image-based loss metrics that consider the full face do not effectively capture the perceptually important, yet spatially small, eye regions. Improving gaze in face swaps can improve naturalness and realism, benefiting applications in entertainment, human computer interaction, and more. Improved gaze will also directly improve Deepfake detection efforts, serving as ideal training data for classifiers that rely on gaze for classification. We propose a novel loss function that leverages gaze prediction to inform the face swap model during training and compare against existing methods. We find all methods to significantly benefit gaze in resulting face swaps.

Abstract: Along with the recent development of deep neural networks, appearance-based gaze estimation has succeeded considerably when training and testing within the same domain. Compared to the within-domain task, the variance of different domains makes the cross-domain performance drop severely, preventing gaze estimation deployment in real-world applications. Among all the factors, ranges of head pose and gaze are believed to play a significant role in the final performance of gaze estimation, while collecting large ranges of data is expensive. This work proposes an effective model training pipeline consisting of a training data synthesis and a gaze estimation model for unsupervised domain adaptation. The proposed data synthesis leverages the single-image 3D reconstruction to expand the range of the head poses from the source domain without requiring a 3D facial shape dataset. To bridge the inevitable gap between synthetic and real images, we further propose an unsupervised domain adaptation method suitable for synthetic full-face data. We propose a disentangling autoencoder network to separate gaze-related features and introduce background augmentation consistency loss to utilize the characteristics of the synthetic source domain. Through comprehensive experiments, we show that the model only using monocular-reconstructed synthetic training data can perform comparably to real data with a large label range. Our proposed domain adaptation approach further improves the performance on multiple target domains. The code and data will be available at \url{https://github.com/ut-vision/AdaptiveGaze}.

Abstract: Scene Text Recognition (STR) is a challenging task due to variations in text style, shape, and background. Incorporating linguistic information is an effective way to enhance the robustness of STR models. Existing methods rely on permuted language modeling (PLM) or masked language modeling (MLM) to learn contextual information implicitly, either through an ensemble of permuted autoregressive (AR) LMs training or iterative non-autoregressive (NAR) decoding procedure. However, these methods exhibit limitations: PLM's AR decoding results in the lack of information about future characters, while MLM provides global information of the entire text but neglects dependencies among each predicted character. In this paper, we propose a Masked and Permuted Implicit Context Learning Network for STR, which unifies PLM and MLM within a single decoding architecture, inheriting the advantages of both approaches. We utilize the training procedure of PLM, and to integrate MLM, we incorporate word length information into the decoding process by introducing specific numbers of mask tokens. Experimental results demonstrate that our proposed model achieves state-of-the-art performance on standard benchmarks using both AR and NAR decoding procedures.

Abstract: Consistency learning plays a crucial role in semi-supervised medical image segmentation as it enables the effective utilization of limited annotated data while leveraging the abundance of unannotated data. The effectiveness and efficiency of consistency learning are challenged by prediction diversity and training stability, which are often overlooked by existing studies. Meanwhile, the limited quantity of labeled data for training often proves inadequate for formulating intra-class compactness and inter-class discrepancy of pseudo labels. To address these issues, we propose a self-aware and cross-sample prototypical learning method (SCP-Net) to enhance the diversity of prediction in consistency learning by utilizing a broader range of semantic information derived from multiple inputs. Furthermore, we introduce a self-aware consistency learning method that exploits unlabeled data to improve the compactness of pseudo labels within each class. Moreover, a dual loss re-weighting method is integrated into the cross-sample prototypical consistency learning method to improve the reliability and stability of our model. Extensive experiments on ACDC dataset and PROMISE12 dataset validate that SCP-Net outperforms other state-of-the-art semi-supervised segmentation methods and achieves significant performance gains compared to the limited supervised training. Our code will come soon.

Abstract: Semi-supervised medical image segmentation offers a promising solution for large-scale medical image analysis by significantly reducing the annotation burden while achieving comparable performance. Employing this method exhibits a high degree of potential for optimizing the segmentation process and increasing its feasibility in clinical settings during translational investigations. Recently, cross-supervised training based on different co-training sub-networks has become a standard paradigm for this task. Still, the critical issues of sub-network disagreement and label-noise suppression require further attention and progress in cross-supervised training. This paper proposes a cross-supervised learning framework based on dual classifiers (DC-Net), including an evidential classifier and a vanilla classifier. The two classifiers exhibit complementary characteristics, enabling them to handle disagreement effectively and generate more robust and accurate pseudo-labels for unlabeled data. We also incorporate the uncertainty estimation from the evidential classifier into cross-supervised training to alleviate the negative effect of the error supervision signal. The extensive experiments on LA and Pancreas-CT dataset illustrate that DC-Net outperforms other state-of-the-art methods for semi-supervised segmentation. The code will be released soon.

Abstract: Segment anything model (SAM) has presented impressive objectness identification capability with the idea of prompt learning and a new collected large-scale dataset. Given a prompt (e.g., points, bounding boxes, or masks) and an input image, SAM is able to generate valid segment masks for all objects indicated by the prompts, presenting high generalization across diverse scenarios and being a general method for zero-shot transfer to downstream vision tasks. Nevertheless, it remains unclear whether SAM may introduce errors in certain threatening scenarios. Clarifying this is of significant importance for applications that require robustness, such as autonomous vehicles. In this paper, we aim to study the testing-time robustness of SAM under adversarial scenarios and common corruptions. To this end, we first build a testing-time robustness evaluation benchmark for SAM by integrating existing public datasets. Second, we extend representative adversarial attacks against SAM and study the influence of different prompts on robustness. Third, we study the robustness of SAM under diverse corruption types by evaluating SAM on corrupted datasets with different prompts. With experiments conducted on SA-1B and KITTI datasets, we find that SAM exhibits remarkable robustness against various corruptions, except for blur-related corruption. Furthermore, SAM remains susceptible to adversarial attacks, particularly when subjected to PGD and BIM attacks. We think such a comprehensive study could highlight the importance of the robustness issues of SAM and trigger a series of new tasks for SAM as well as downstream vision tasks.

Abstract: Text-to-image (T2I) research has grown explosively in the past year, owing to the large-scale pre-trained diffusion models and many emerging personalization and editing approaches. Yet, one pain point persists: the text prompt engineering, and searching high-quality text prompts for customized results is more art than science. Moreover, as commonly argued: "an image is worth a thousand words" - the attempt to describe a desired image with texts often ends up being ambiguous and cannot comprehensively cover delicate visual details, hence necessitating more additional controls from the visual domain. In this paper, we take a bold step forward: taking "Text" out of a pre-trained T2I diffusion model, to reduce the burdensome prompt engineering efforts for users. Our proposed framework, Prompt-Free Diffusion, relies on only visual inputs to generate new images: it takes a reference image as "context", an optional image structural conditioning, and an initial noise, with absolutely no text prompt. The core architecture behind the scene is Semantic Context Encoder (SeeCoder), substituting the commonly used CLIP-based or LLM-based text encoder. The reusability of SeeCoder also makes it a convenient drop-in component: one can also pre-train a SeeCoder in one T2I model and reuse it for another. Through extensive experiments, Prompt-Free Diffusion is experimentally found to (i) outperform prior exemplar-based image synthesis approaches; (ii) perform on par with state-of-the-art T2I models using prompts following the best practice; and (iii) be naturally extensible to other downstream applications such as anime figure generation and virtual try-on, with promising quality. Our code and models are open-sourced at https://github.com/SHI-Labs/Prompt-Free-Diffusion.

Abstract: This paper investigates the potential of enhancing Neural Radiance Fields (NeRF) with semantics to expand their applications. Although NeRF has been proven useful in real-world applications like VR and digital creation, the lack of semantics hinders interaction with objects in complex scenes. We propose to imitate the backbone feature of off-the-shelf perception models to achieve zero-shot semantic segmentation with NeRF. Our framework reformulates the segmentation process by directly rendering semantic features and only applying the decoder from perception models. This eliminates the need for expensive backbones and benefits 3D consistency. Furthermore, we can project the learned semantics onto extracted mesh surfaces for real-time interaction. With the state-of-the-art Segment Anything Model (SAM), our framework accelerates segmentation by 16 times with comparable mask quality. The experimental results demonstrate the efficacy and computational advantages of our approach. Project page: \url{https://me.kiui.moe/san/}.

Abstract: In recent years, Denoising Diffusion Probabilistic Models (DDPM) have caught significant attention. By composing a Markovian process that starts in the data domain and then gradually adds noise until reaching pure white noise, they achieve superior performance in learning data distributions. Yet, these models require a large number of diffusion steps to produce aesthetically pleasing samples, which is inefficient. In addition, unlike common generative adversarial networks, the latent space of diffusion models is not interpretable. In this work, we propose to generalize the denoising diffusion process into an Upsampling Diffusion Probabilistic Model (UDPM), in which we reduce the latent variable dimension in addition to the traditional noise level addition. As a result, we are able to sample images of size $256\times 256$ with only 7 diffusion steps, which is less than two orders of magnitude compared to standard DDPMs. We formally develop the Markovian diffusion processes of the UDPM, and demonstrate its generation capabilities on the popular FFHQ, LSUN horses, ImageNet, and AFHQv2 datasets. Another favorable property of UDPM is that it is very easy to interpolate its latent space, which is not the case with standard diffusion models. Our code is available online \url{https://github.com/shadyabh/UDPM}

Abstract: Progress in Automated Handwriting Recognition has been hampered by the lack of large training datasets. Nearly all research uses a set of small datasets that often cause models to overfit. We present CENSUS-HWR, a new dataset consisting of full English handwritten words in 1,812,014 gray scale images. A total of 1,865,134 handwritten texts from a vocabulary of 10,711 words in the English language are present in this collection. This dataset is intended to serve handwriting models as a benchmark for deep learning algorithms. This huge English handwriting recognition dataset has been extracted from the US 1930 and 1940 censuses taken by approximately 70,000 enumerators each year. The dataset and the trained model with their weights are freely available to download at https://censustree.org/data.html.

Abstract: Controllable scene synthesis aims to create interactive environments for various industrial use cases. Scene graphs provide a highly suitable interface to facilitate these applications by abstracting the scene context in a compact manner. Existing methods, reliant on retrieval from extensive databases or pre-trained shape embeddings, often overlook scene-object and object-object relationships, leading to inconsistent results due to their limited generation capacity. To address this issue, we present CommonScenes, a fully generative model that converts scene graphs into corresponding controllable 3D scenes, which are semantically realistic and conform to commonsense. Our pipeline consists of two branches, one predicting the overall scene layout via a variational auto-encoder and the other generating compatible shapes via latent diffusion, capturing global scene-object and local inter-object relationships while preserving shape diversity. The generated scenes can be manipulated by editing the input scene graph and sampling the noise in the diffusion model. Due to lacking a scene graph dataset offering high-quality object-level meshes with relations, we also construct SG-FRONT, enriching the off-the-shelf indoor dataset 3D-FRONT with additional scene graph labels. Extensive experiments are conducted on SG-FRONT where CommonScenes shows clear advantages over other methods regarding generation consistency, quality, and diversity. Codes and the dataset will be released upon acceptance.

Abstract: Many fine-grained classification tasks, like rare animal identification, have limited training data and consequently classifiers trained on these datasets often fail to generalize to variations in the domain like changes in weather or location. As such, we explore how natural language descriptions of the domains seen in training data can be used with large vision models trained on diverse pretraining datasets to generate useful variations of the training data. We introduce ALIA (Automated Language-guided Image Augmentation), a method which utilizes large vision and language models to automatically generate natural language descriptions of a dataset's domains and augment the training data via language-guided image editing. To maintain data integrity, a model trained on the original dataset filters out minimal image edits and those which corrupt class-relevant information. The resulting dataset is visually consistent with the original training data and offers significantly enhanced diversity. On fine-grained and cluttered datasets for classification and detection, ALIA surpasses traditional data augmentation and text-to-image generated data by up to 15\%, often even outperforming equivalent additions of real data. Code is avilable at https://github.com/lisadunlap/ALIA.

Abstract: A great deal of progress has been made in image captioning, driven by research into how to encode the image using pre-trained models. This includes visual encodings (e.g. image grid features or detected objects) and more recently textual encodings (e.g. image tags or text descriptions of image regions). As more advanced encodings are available and incorporated, it is natural to ask: how to efficiently and effectively leverage the heterogeneous set of encodings? In this paper, we propose to regard the encodings as augmented views of the input image. The image captioning model encodes each view independently with a shared encoder efficiently, and a contrastive loss is incorporated across the encoded views in a novel way to improve their representation quality and the model's data efficiency. Our proposed hierarchical decoder then adaptively weighs the encoded views according to their effectiveness for caption generation by first aggregating within each view at the token level, and then across views at the view level. We demonstrate significant performance improvements of +5.6% CIDEr on MS-COCO and +12.9% CIDEr on Flickr30k compared to state of the arts, and conduct rigorous analyses to demonstrate the importance of each part of our design.

Abstract: The analysis and use of egocentric videos for robotic tasks is made challenging by occlusion due to the hand and the visual mismatch between the human hand and a robot end-effector. In this sense, the human hand presents a nuisance. However, often hands also provide a valuable signal, e.g. the hand pose may suggest what kind of object is being held. In this work, we propose to extract a factored representation of the scene that separates the agent (human hand) and the environment. This alleviates both occlusion and mismatch while preserving the signal, thereby easing the design of models for downstream robotics tasks. At the heart of this factorization is our proposed Video Inpainting via Diffusion Model (VIDM) that leverages both a prior on real-world images (through a large-scale pre-trained diffusion model) and the appearance of the object in earlier frames of the video (through attention). Our experiments demonstrate the effectiveness of VIDM at improving inpainting quality on egocentric videos and the power of our factored representation for numerous tasks: object detection, 3D reconstruction of manipulated objects, and learning of reward functions, policies, and affordances from videos.

Abstract: Composed image retrieval aims to find an image that best matches a given multi-modal user query consisting of a reference image and text pair. Existing methods commonly pre-compute image embeddings over the entire corpus and compare these to a reference image embedding modified by the query text at test time. Such a pipeline is very efficient at test time since fast vector distances can be used to evaluate candidates, but modifying the reference image embedding guided only by a short textual description can be difficult, especially independent of potential candidates. An alternative approach is to allow interactions between the query and every possible candidate, i.e., reference-text-candidate triplets, and pick the best from the entire set. Though this approach is more discriminative, for large-scale datasets the computational cost is prohibitive since pre-computation of candidate embeddings is no longer possible. We propose to combine the merits of both schemes using a two-stage model. Our first stage adopts the conventional vector distancing metric and performs a fast pruning among candidates. Meanwhile, our second stage employs a dual-encoder architecture, which effectively attends to the input triplet of reference-text-candidate and re-ranks the candidates. Both stages utilize a vision-and-language pre-trained network, which has proven beneficial for various downstream tasks. Our method consistently outperforms state-of-the-art approaches on standard benchmarks for the task.

Abstract: Recent advances in deep generative models have led to the development of methods capable of synthesizing high-quality, realistic images. These models pose threats to society due to their potential misuse. Prior research attempted to mitigate these threats by detecting generated images, but the varying traces left by different generative models make it challenging to create a universal detector capable of generalizing to new, unseen generative models. In this paper, we propose to inject a universal adversarial signature into an arbitrary pre-trained generative model, in order to make its generated contents more detectable and traceable. First, the imperceptible optimal signature for each image can be found by a signature injector through adversarial training. Subsequently, the signature can be incorporated into an arbitrary generator by fine-tuning it with the images processed by the signature injector. In this way, the detector corresponding to the signature can be reused for any fine-tuned generator for tracking the generator identity. The proposed method is validated on the FFHQ and ImageNet datasets with various state-of-the-art generative models, consistently showing a promising detection rate. Code will be made publicly available at \url{https://github.com/zengxianyu/genwm}.

Abstract: Text-to-image model personalization aims to introduce a user-provided concept to the model, allowing its synthesis in diverse contexts. However, current methods primarily focus on the case of learning a single concept from multiple images with variations in backgrounds and poses, and struggle when adapted to a different scenario. In this work, we introduce the task of textual scene decomposition: given a single image of a scene that may contain several concepts, we aim to extract a distinct text token for each concept, enabling fine-grained control over the generated scenes. To this end, we propose augmenting the input image with masks that indicate the presence of target concepts. These masks can be provided by the user or generated automatically by a pre-trained segmentation model. We then present a novel two-phase customization process that optimizes a set of dedicated textual embeddings (handles), as well as the model weights, striking a delicate balance between accurately capturing the concepts and avoiding overfitting. We employ a masked diffusion loss to enable handles to generate their assigned concepts, complemented by a novel loss on cross-attention maps to prevent entanglement. We also introduce union-sampling, a training strategy aimed to improve the ability of combining multiple concepts in generated images. We use several automatic metrics to quantitatively compare our method against several baselines, and further affirm the results using a user study. Finally, we showcase several applications of our method. Project page is available at: https://omriavrahami.com/break-a-scene/

Abstract: We propose a learning-based method to recover normals, specularity, and roughness from a single diffuse image of a material, using microgeometry appearance as our primary cue. Previous methods that work on single images tend to produce over-smooth outputs with artifacts, operate at limited resolution, or train one model per class with little room for generalization. Previous methods that work on single images tend to produce over-smooth outputs with artifacts, operate at limited resolution, or train one model per class with little room for generalization. In contrast, in this work, we propose a novel capture approach that leverages a generative network with attention and a U-Net discriminator, which shows outstanding performance integrating global information at reduced computational complexity. We showcase the performance of our method with a real dataset of digitized textile materials and show that a commodity flatbed scanner can produce the type of diffuse illumination required as input to our method. Additionally, because the problem might be illposed -more than a single diffuse image might be needed to disambiguate the specular reflection- or because the training dataset is not representative enough of the real distribution, we propose a novel framework to quantify the model's confidence about its prediction at test time. Our method is the first one to deal with the problem of modeling uncertainty in material digitization, increasing the trustworthiness of the process and enabling more intelligent strategies for dataset creation, as we demonstrate with an active learning experiment.

Abstract: Equivariance has gained strong interest as a desirable network property that inherently ensures robust generalization. However, when dealing with complex systems such as articulated objects or multi-object scenes, effectively capturing inter-part transformations poses a challenge, as it becomes entangled with the overall structure and local transformations. The interdependence of part assignment and per-part group action necessitates a novel equivariance formulation that allows for their co-evolution. In this paper, we present Banana, a Banach fixed-point network for equivariant segmentation with inter-part equivariance by construction. Our key insight is to iteratively solve a fixed-point problem, where point-part assignment labels and per-part SE(3)-equivariance co-evolve simultaneously. We provide theoretical derivations of both per-step equivariance and global convergence, which induces an equivariant final convergent state. Our formulation naturally provides a strict definition of inter-part equivariance that generalizes to unseen inter-part configurations. Through experiments conducted on both articulated objects and multi-object scans, we demonstrate the efficacy of our approach in achieving strong generalization under inter-part transformations, even when confronted with substantial changes in pointcloud geometry and topology.

Abstract: We propose Neural 3D Articulation Prior (NAP), the first 3D deep generative model to synthesize 3D articulated object models. Despite the extensive research on generating 3D objects, compositions, or scenes, there remains a lack of focus on capturing the distribution of articulated objects, a common object category for human and robot interaction. To generate articulated objects, we first design a novel articulation tree/graph parameterization and then apply a diffusion-denoising probabilistic model over this representation where articulated objects can be generated via denoising from random complete graphs. In order to capture both the geometry and the motion structure whose distribution will affect each other, we design a graph-attention denoising network for learning the reverse diffusion process. We propose a novel distance that adapts widely used 3D generation metrics to our novel task to evaluate generation quality, and experiments demonstrate our high performance in articulated object generation. We also demonstrate several conditioned generation applications, including Part2Motion, PartNet-Imagination, Motion2Part, and GAPart2Object.

Abstract: For computer vision tasks, Vision Transformers (ViTs) have become one of the go-to deep net architectures. Despite being inspired by Convolutional Neural Networks (CNNs), ViTs remain sensitive to small shifts in the input image. To address this, we introduce novel designs for each of the modules in ViTs, such as tokenization, self-attention, patch merging, and positional encoding. With our proposed modules, we achieve truly shift-equivariant ViTs on four well-established models, namely, Swin, SwinV2, MViTv2, and CvT, both in theory and practice. Empirically, we tested these models on image classification and semantic segmentation, achieving competitive performance across three different datasets while maintaining 100% shift consistency.

Abstract: Recently, video object segmentation (VOS) referred by multi-modal signals, e.g., language and audio, has evoked increasing attention in both industry and academia. It is challenging for exploring the semantic alignment within modalities and the visual correspondence across frames. However, existing methods adopt separate network architectures for different modalities, and neglect the inter-frame temporal interaction with references. In this paper, we propose MUTR, a Multi-modal Unified Temporal transformer for Referring video object segmentation. With a unified framework for the first time, MUTR adopts a DETR-style transformer and is capable of segmenting video objects designated by either text or audio reference. Specifically, we introduce two strategies to fully explore the temporal relations between videos and multi-modal signals. Firstly, for low-level temporal aggregation before the transformer, we enable the multi-modal references to capture multi-scale visual cues from consecutive video frames. This effectively endows the text or audio signals with temporal knowledge and boosts the semantic alignment between modalities. Secondly, for high-level temporal interaction after the transformer, we conduct inter-frame feature communication for different object embeddings, contributing to better object-wise correspondence for tracking along the video. On Ref-YouTube-VOS and AVSBench datasets with respective text and audio references, MUTR achieves +4.2% and +4.2% J&F improvements to state-of-the-art methods, demonstrating our significance for unified multi-modal VOS. Code is released at https://github.com/OpenGVLab/MUTR.

Abstract: This paper reveals that every image can be understood as a first-order norm+linear autoregressive process, referred to as FINOLA, where norm+linear denotes the use of normalization before the linear model. We demonstrate that images of size 256$\times$256 can be reconstructed from a compressed vector using autoregression up to a 16$\times$16 feature map, followed by upsampling and convolution. This discovery sheds light on the underlying partial differential equations (PDEs) governing the latent feature space. Additionally, we investigate the application of FINOLA for self-supervised learning through a simple masked prediction technique. By encoding a single unmasked quadrant block, we can autoregressively predict the surrounding masked region. Remarkably, this pre-trained representation proves effective for image classification and object detection tasks, even in lightweight networks, without requiring fine-tuning. The code will be made publicly available.

Abstract: Decomposing an object's appearance into representations of its materials and the surrounding illumination is difficult, even when the object's 3D shape is known beforehand. This problem is ill-conditioned because diffuse materials severely blur incoming light, and is ill-posed because diffuse materials under high-frequency lighting can be indistinguishable from shiny materials under low-frequency lighting. We show that it is possible to recover precise materials and illumination -- even from diffuse objects -- by exploiting unintended shadows, like the ones cast onto an object by the photographer who moves around it. These shadows are a nuisance in most previous inverse rendering pipelines, but here we exploit them as signals that improve conditioning and help resolve material-lighting ambiguities. We present a method based on differentiable Monte Carlo ray tracing that uses images of an object to jointly recover its spatially-varying materials, the surrounding illumination environment, and the shapes of the unseen light occluders who inadvertently cast shadows upon it.

Abstract: Text-to-Image diffusion models have made tremendous progress over the past two years, enabling the generation of highly realistic images based on open-domain text descriptions. However, despite their success, text descriptions often struggle to adequately convey detailed controls, even when composed of long and complex texts. Moreover, recent studies have also shown that these models face challenges in understanding such complex texts and generating the corresponding images. Therefore, there is a growing need to enable more control modes beyond text description. In this paper, we introduce Uni-ControlNet, a novel approach that allows for the simultaneous utilization of different local controls (e.g., edge maps, depth map, segmentation masks) and global controls (e.g., CLIP image embeddings) in a flexible and composable manner within one model. Unlike existing methods, Uni-ControlNet only requires the fine-tuning of two additional adapters upon frozen pre-trained text-to-image diffusion models, eliminating the huge cost of training from scratch. Moreover, thanks to some dedicated adapter designs, Uni-ControlNet only necessitates a constant number (i.e., 2) of adapters, regardless of the number of local or global controls used. This not only reduces the fine-tuning costs and model size, making it more suitable for real-world deployment, but also facilitate composability of different conditions. Through both quantitative and qualitative comparisons, Uni-ControlNet demonstrates its superiority over existing methods in terms of controllability, generation quality and composability. Code is available at \url{https://github.com/ShihaoZhaoZSH/Uni-ControlNet}.

Abstract: Text-conditioned image generation models have recently shown immense qualitative success using denoising diffusion processes. However, unlike discriminative vision-and-language models, it is a non-trivial task to subject these diffusion-based generative models to automatic fine-grained quantitative evaluation of high-level phenomena such as compositionality. Towards this goal, we perform two innovations. First, we transform diffusion-based models (in our case, Stable Diffusion) for any image-text matching (ITM) task using a novel method called DiffusionITM. Second, we introduce the Generative-Discriminative Evaluation Benchmark (GDBench) benchmark with 7 complex vision-and-language tasks, bias evaluation and detailed analysis. We find that Stable Diffusion + DiffusionITM is competitive on many tasks and outperforms CLIP on compositional tasks like like CLEVR and Winoground. We further boost its compositional performance with a transfer setup by fine-tuning on MS-COCO while retaining generative capabilities. We also measure the stereotypical bias in diffusion models, and find that Stable Diffusion 2.1 is, for the most part, less biased than Stable Diffusion 1.5. Overall, our results point in an exciting direction bringing discriminative and generative model evaluation closer. We will release code and benchmark setup soon.

Abstract: We study the problem of 3D semantic segmentation from raw point clouds. Unlike existing methods which primarily rely on a large amount of human annotations for training neural networks, we propose the first purely unsupervised method, called GrowSP, to successfully identify complex semantic classes for every point in 3D scenes, without needing any type of human labels or pretrained models. The key to our approach is to discover 3D semantic elements via progressive growing of superpoints. Our method consists of three major components, 1) the feature extractor to learn per-point features from input point clouds, 2) the superpoint constructor to progressively grow the sizes of superpoints, and 3) the semantic primitive clustering module to group superpoints into semantic elements for the final semantic segmentation. We extensively evaluate our method on multiple datasets, demonstrating superior performance over all unsupervised baselines and approaching the classic fully-supervised PointNet. We hope our work could inspire more advanced methods for unsupervised 3D semantic learning.

Abstract: Recent advancements in text-to-image generation have enabled significant progress in zero-shot 3D shape generation. This is achieved by score distillation, a methodology that uses pre-trained text-to-image diffusion models to optimize the parameters of a 3D neural presentation, e.g. Neural Radiance Field (NeRF). While showing promising results, existing methods are often not able to preserve the geometry of complex shapes, such as human bodies. To address this challenge, we present ZeroAvatar, a method that introduces the explicit 3D human body prior to the optimization process. Specifically, we first estimate and refine the parameters of a parametric human body from a single image. Then during optimization, we use the posed parametric body as additional geometry constraint to regularize the diffusion model as well as the underlying density field. Lastly, we propose a UV-guided texture regularization term to further guide the completion of texture on invisible body parts. We show that ZeroAvatar significantly enhances the robustness and 3D consistency of optimization-based image-to-3D avatar generation, outperforming existing zero-shot image-to-3D methods.

Abstract: In the realm of facial analysis, accurate landmark detection is crucial for various applications, ranging from face recognition and expression analysis to animation. Conventional heatmap or coordinate regression-based techniques, however, often face challenges in terms of computational burden and quantization errors. To address these issues, we present the KeyPoint Positioning System (KeyPosS), a groundbreaking facial landmark detection framework that stands out from existing methods. For the first time, KeyPosS employs the True-range Multilateration algorithm, a technique originally used in GPS systems, to achieve rapid and precise facial landmark detection without relying on computationally intensive regression approaches. The framework utilizes a fully convolutional network to predict a distance map, which computes the distance between a Point of Interest (POI) and multiple anchor points. These anchor points are ingeniously harnessed to triangulate the POI's position through the True-range Multilateration algorithm. Notably, the plug-and-play nature of KeyPosS enables seamless integration into any decoding stage, ensuring a versatile and adaptable solution. We conducted a thorough evaluation of KeyPosS's performance by benchmarking it against state-of-the-art models on four different datasets. The results show that KeyPosS substantially outperforms leading methods in low-resolution settings while requiring a minimal time overhead. The code is available at https://github.com/zhiqic/KeyPosS.

Abstract: Face recognition algorithms perform more accurately than humans in some cases, though humans and machines both show race-based accuracy differences. As algorithms continue to improve, it is important to continually assess their race bias relative to humans. We constructed a challenging test of 'cross-race' face verification and used it to compare humans and two state-of-the-art face recognition systems. Pairs of same- and different-identity faces of White and Black individuals were selected to be difficult for humans and an open-source implementation of the ArcFace face recognition algorithm from 2019 (5). Human participants (54 Black; 51 White) judged whether face pairs showed the same identity or different identities on a 7-point Likert-type scale. Two top-performing face recognition systems from the Face Recognition Vendor Test-ongoing performed the same test (7). By design, the test proved challenging for humans as a group, who performed above chance, but far less than perfect. Both state-of-the-art face recognition systems scored perfectly (no errors), consequently with equal accuracy for both races. We conclude that state-of-the-art systems for identity verification between two frontal face images of Black and White individuals can surpass the general population. Whether this result generalizes to challenging in-the-wild images is a pressing concern for deploying face recognition systems in unconstrained environments.

Abstract: To detect UAVs in real-time, computer vision and deep learning approaches are developing areas of research. There have been concerns raised regarding the possible hazards and misuse of employing unmanned aerial vehicles (UAVs) in many applications. These include potential privacy violations, safety-related issues, and security threats. Vision-based detection systems often comprise a combination of hardware components such as cameras and software components. In this work, the performance of recent and popular vision-based object detection techniques is investigated for the task of UAV detection under challenging conditions such as complex backgrounds, varying UAV sizes, complex background scenarios, and low-to-heavy rainy conditions. To study the performance of selected methods under these conditions, two datasets were curated: one with a sky background and one with complex background. In this paper, one-stage detectors and two-stage detectors are studied and evaluated. The findings presented in the paper shall help provide insights concerning the performance of the selected models for the task of UAV detection under challenging conditions and pave the way to develop more robust UAV detection methods

Abstract: Accurately quantifying and removing submerged underwater waste plays a crucial role in safeguarding marine life and preserving the environment. While detecting floating and surface debris is relatively straightforward, quantifying submerged waste presents significant challenges due to factors like light refraction, absorption, suspended particles, and color distortion. This paper addresses these challenges by proposing the development of a custom dataset and an efficient detection approach for submerged marine debris. The dataset encompasses diverse underwater environments and incorporates annotations for precise labeling of debris instances. Ultimately, the primary objective of this custom dataset is to enhance the diversity of litter instances and improve their detection accuracy in deep submerged environments by leveraging state-of-the-art deep learning architectures.

Abstract: Deep models have demonstrated recent success in single-image dehazing. Most prior methods consider fully supervised training and learn from paired clean and hazy images, where a hazy image is synthesized based on a clean image and its estimated depth map. This paradigm, however, can produce low-quality hazy images due to inaccurate depth estimation, resulting in poor generalization of the trained models. In this paper, we explore an alternative approach for generating paired clean-hazy images by leveraging computer graphics. Using a modern game engine, our approach renders crisp clean images and their precise depth maps, based on which high-quality hazy images can be synthesized for training dehazing models. To this end, we present SimHaze: a new synthetic haze dataset. More importantly, we show that training with SimHaze alone allows the latest dehazing models to achieve significantly better performance in comparison to previous dehazing datasets. Our dataset and code will be made publicly available.

Abstract: We present EgoHumans, a new multi-view multi-human video benchmark to advance the state-of-the-art of egocentric human 3D pose estimation and tracking. Existing egocentric benchmarks either capture single subject or indoor-only scenarios, which limit the generalization of computer vision algorithms for real-world applications. We propose a novel 3D capture setup to construct a comprehensive egocentric multi-human benchmark in the wild with annotations to support diverse tasks such as human detection, tracking, 2D/3D pose estimation, and mesh recovery. We leverage consumer-grade wearable camera-equipped glasses for the egocentric view, which enables us to capture dynamic activities like playing soccer, fencing, volleyball, etc. Furthermore, our multi-view setup generates accurate 3D ground truth even under severe or complete occlusion. The dataset consists of more than 125k egocentric images, spanning diverse scenes with a particular focus on challenging and unchoreographed multi-human activities and fast-moving egocentric views. We rigorously evaluate existing state-of-the-art methods and highlight their limitations in the egocentric scenario, specifically on multi-human tracking. To address such limitations, we propose EgoFormer, a novel approach with a multi-stream transformer architecture and explicit 3D spatial reasoning to estimate and track the human pose. EgoFormer significantly outperforms prior art by 13.6% IDF1 and 9.3 HOTA on the EgoHumans dataset.

Abstract: Stroke is one of two main causes of death worldwide. Many individuals suffer from ischemic stroke every year. Only in US more over 700,000 individuals meet ischemic stroke due to blood clot blocking an artery to the brain every year. The paper describes particular approach how to apply Artificial Intelligence for purposes of separating two major acute ischemic stroke (AIS) etiology subtypes: cardiac and large artery atherosclerosis. Four deep neural network architectures and simple ensemble method are used in the approach.

Abstract: Neural networks are known to be susceptible to adversarial samples: small variations of natural examples crafted to deliberately mislead the models. While they can be easily generated using gradient-based techniques in digital and physical scenarios, they often differ greatly from the actual data distribution of natural images, resulting in a trade-off between strength and stealthiness. In this paper, we propose a novel framework dubbed Diffusion-Based Projected Gradient Descent (Diff-PGD) for generating realistic adversarial samples. By exploiting a gradient guided by a diffusion model, Diff-PGD ensures that adversarial samples remain close to the original data distribution while maintaining their effectiveness. Moreover, our framework can be easily customized for specific tasks such as digital attacks, physical-world attacks, and style-based attacks. Compared with existing methods for generating natural-style adversarial samples, our framework enables the separation of optimizing adversarial loss from other surrogate losses (e.g., content/smoothness/style loss), making it more stable and controllable. Finally, we demonstrate that the samples generated using Diff-PGD have better transferability and anti-purification power than traditional gradient-based methods. Code will be released in https://github.com/xavihart/Diff-PGD

Abstract: As the deployment of computer vision technology becomes increasingly common in applications of consequence such as medicine or science, the need for explanations of the system output has become a focus of great concern. Unfortunately, many state-of-the-art computer vision models are opaque, making their use challenging from an explanation standpoint, and current approaches to explaining these opaque models have stark limitations and have been the subject of serious criticism. In contrast, Explainable Boosting Machines (EBMs) are a class of models that are easy to interpret and achieve performance on par with the very best-performing models, however, to date EBMs have been limited solely to tabular data. Driven by the pressing need for interpretable models in science, we propose the use of EBMs for scientific image data. Inspired by an important application underpinning the development of quantum technologies, we apply EBMs to cold-atom soliton image data, and, in doing so, demonstrate EBMs for image data for the first time. To tabularize the image data we employ Gabor Wavelet Transform-based techniques that preserve the spatial structure of the data. We show that our approach provides better explanations than other state-of-the-art explainability methods for images.