Computer Vision and Pattern Recognition (cs.CV)

Abstract: In digital images, the performance of optical aberration is a multivariate degradation, where the spectral of the scene, the lens imperfections, and the field of view together contribute to the results. Besides eliminating it at the hardware level, the post-processing system, which utilizes various prior information, is significant for correction. However, due to the content differences among priors, the pipeline that aligns these factors shows limited efficiency and unoptimized restoration. Here, we propose a prior quantization model to correct the optical aberrations in image processing systems. To integrate these messages, we encode various priors into a latent space and quantify them by the learnable codebooks. After quantization, the prior codes are fused with the image restoration branch to realize targeted optical aberration correction. Comprehensive experiments demonstrate the flexibility of the proposed method and validate its potential to accomplish targeted restoration for a specific camera. Furthermore, our model promises to analyze the correlation between the various priors and the optical aberration of devices, which is helpful for joint soft-hardware design.

Abstract: With the advent of depth-to-image diffusion models, text-guided generation, editing, and transfer of realistic textures are no longer difficult. However, due to the limitations of pre-trained diffusion models, they can only create low-resolution, inconsistent textures. To address this issue, we present the High-definition Consistency Texture Model (HCTM), a novel method that can generate high-definition and consistent textures for 3D meshes according to the text prompts. We achieve this by leveraging a pre-trained depth-to-image diffusion model to generate single viewpoint results based on the text prompt and a depth map. We fine-tune the diffusion model with Parameter-Efficient Fine-Tuning to quickly learn the style of the generated result, and apply the multi-diffusion strategy to produce high-resolution and consistent results from different viewpoints. Furthermore, we propose a strategy that prevents the appearance of noise on the textures caused by backpropagation. Our proposed approach has demonstrated promising results in generating high-definition and consistent textures for 3D meshes, as demonstrated through a series of experiments.

Abstract: Dunhuang murals suffer from fading, breakage, surface brittleness and extensive peeling affected by prolonged environmental erosion. Image inpainting techniques are widely used in the field of digital mural inpainting. Generally speaking, for mural inpainting tasks with large area damage, it is challenging for any image inpainting method. In this paper, we design a multi-stage progressive reasoning network (MPR-Net) containing global to local receptive fields for murals inpainting. This network is capable of recursively inferring the damage boundary and progressively tightening the regional texture constraints. Moreover, to adaptively fuse plentiful information at various scales of murals, a multi-scale feature aggregation module (MFA) is designed to empower the capability to select the significant features. The execution of the model is similar to the process of a mural restorer (i.e., inpainting the structure of the damaged mural globally first and then adding the local texture details further). Our method has been evaluated through both qualitative and quantitative experiments, and the results demonstrate that it outperforms state-of-the-art image inpainting methods.

Abstract: Utilizing infrastructure and vehicle-side information to track and forecast the behaviors of surrounding traffic participants can significantly improve decision-making and safety in autonomous driving. However, the lack of real-world sequential datasets limits research in this area. To address this issue, we introduce V2X-Seq, the first large-scale sequential V2X dataset, which includes data frames, trajectories, vector maps, and traffic lights captured from natural scenery. V2X-Seq comprises two parts: the sequential perception dataset, which includes more than 15,000 frames captured from 95 scenarios, and the trajectory forecasting dataset, which contains about 80,000 infrastructure-view scenarios, 80,000 vehicle-view scenarios, and 50,000 cooperative-view scenarios captured from 28 intersections' areas, covering 672 hours of data. Based on V2X-Seq, we introduce three new tasks for vehicle-infrastructure cooperative (VIC) autonomous driving: VIC3D Tracking, Online-VIC Forecasting, and Offline-VIC Forecasting. We also provide benchmarks for the introduced tasks. Find data, code, and more up-to-date information at \href{https://github.com/AIR-THU/DAIR-V2X-Seq}{https://github.com/AIR-THU/DAIR-V2X-Seq}.

Abstract: Diffusion models (DMs) can generate realistic images with text guidance using large-scale datasets. However, they demonstrate limited controllability in the output space of the generated images. We propose a novel learning method for text-guided image editing, namely \texttt{iEdit}, that generates images conditioned on a source image and a textual edit prompt. As a fully-annotated dataset with target images does not exist, previous approaches perform subject-specific fine-tuning at test time or adopt contrastive learning without a target image, leading to issues on preserving the fidelity of the source image. We propose to automatically construct a dataset derived from LAION-5B, containing pseudo-target images with their descriptive edit prompts given input image-caption pairs. This dataset gives us the flexibility of introducing a weakly-supervised loss function to generate the pseudo-target image from the latent noise of the source image conditioned on the edit prompt. To encourage localised editing and preserve or modify spatial structures in the image, we propose a loss function that uses segmentation masks to guide the editing during training and optionally at inference. Our model is trained on the constructed dataset with 200K samples and constrained GPU resources. It shows favourable results against its counterparts in terms of image fidelity, CLIP alignment score and qualitatively for editing both generated and real images.

Abstract: Numerous ideas have emerged for designing fusion rules in the image fusion field. Essentially, all the existing formulations try to manage the diverse levels of information communicated by the source images to achieve the best fusion result. We argue that there is a scope for improving the performance of existing methods further with the help of FusionBooster, a fusion guidance method proposed in this paper. Our booster is based on the divide and conquer strategy controlled by an information probe. The booster is composed of three building blocks: the probe units, the booster layer, and the assembling module. Given the embedding produced by a backbone method, the probe units assess the source images and divide them according to their information content. This is instrumental in identifying missing information, as a step to its recovery. The recovery of the degraded components along with the fusion guidance are embedded in the booster layer. Lastly, the assembling module is responsible for piecing these advanced components together to deliver the output. We use concise reconstruction loss functions and lightweight models to formulate the network, with marginal computational increase. The experimental results obtained in various fusion tasks, as well as downstream detection tasks, consistently demonstrate that the proposed FusionBooster significantly improves the performance. Our codes will be publicly available on the project homepage.

Abstract: LiDAR sensors are critical for autonomous driving and robotics applications due to their ability to provide accurate range measurements and their robustness to lighting conditions. However, airborne particles, such as fog, rain, snow, and dust, will degrade its performance and it is inevitable to encounter these inclement environmental conditions outdoors. It would be a straightforward approach to remove them by supervised semantic segmentation. But annotating these particles point wisely is too laborious. To address this problem and enhance the perception under inclement conditions, we develop two dynamic filtering methods called Dynamic Multi-threshold Noise Removal (DMNR) and DMNR-H by accurate analysis of the position distribution and intensity characteristics of noisy points and clean points on publicly available WADS and DENSE datasets. Both DMNR and DMNR-H outperform state-of-the-art unsupervised methods by a significant margin on the two datasets and are slightly better than supervised deep learning-based methods. Furthermore, our methods are more robust to different LiDAR sensors and airborne particles, such as snow and fog.

Abstract: Existing multimodal conditional image synthesis (MCIS) methods generate images conditioned on any combinations of various modalities that require all of them must be exactly conformed, hindering the synthesis controllability and leaving the potential of cross-modality under-exploited. To this end, we propose to generate images conditioned on the compositions of multimodal control signals, where modalities are imperfectly complementary, i.e., composed multimodal conditional image synthesis (CMCIS). Specifically, we observe two challenging issues of the proposed CMCIS task, i.e., the modality coordination problem and the modality imbalance problem. To tackle these issues, we introduce a Mixture-of-Modality-Tokens Transformer (MMoT) that adaptively fuses fine-grained multimodal control signals, a multimodal balanced training loss to stabilize the optimization of each modality, and a multimodal sampling guidance to balance the strength of each modality control signal. Comprehensive experimental results demonstrate that MMoT achieves superior performance on both unimodal conditional image synthesis (UCIS) and MCIS tasks with high-quality and faithful image synthesis on complex multimodal conditions. The project website is available at https://jabir-zheng.github.io/MMoT.

Abstract: Automatic image captioning evaluation is critical for benchmarking and promoting advances in image captioning research. Existing metrics only provide a single score to measure caption qualities, which are less explainable and informative. Instead, we humans can easily identify the problems of captions in details, e.g., which words are inaccurate and which salient objects are not described, and then rate the caption quality. To support such informative feedback, we propose an Informative Metric for Reference-free Image Caption evaluation (InfoMetIC). Given an image and a caption, InfoMetIC is able to report incorrect words and unmentioned image regions at fine-grained level, and also provide a text precision score, a vision recall score and an overall quality score at coarse-grained level. The coarse-grained score of InfoMetIC achieves significantly better correlation with human judgements than existing metrics on multiple benchmarks. We also construct a token-level evaluation dataset and demonstrate the effectiveness of InfoMetIC in fine-grained evaluation. Our code and datasets are publicly available at https://github.com/HAWLYQ/InfoMetIC.

Abstract: The performance of computer vision models is susceptible to unexpected changes in input images when deployed in real scenarios. These changes are referred to as common corruptions. While they can hinder the applicability of computer vision models in real-world scenarios, they are not always considered as a testbed for model generalization and robustness. In this survey, we present a comprehensive and systematic overview of methods that improve corruption robustness of computer vision models. Unlike existing surveys that focus on adversarial attacks and label noise, we cover extensively the study of robustness to common corruptions that can occur when deploying computer vision models to work in practical applications. We describe different types of image corruption and provide the definition of corruption robustness. We then introduce relevant evaluation metrics and benchmark datasets. We categorize methods into four groups. We also cover indirect methods that show improvements in generalization and may improve corruption robustness as a byproduct. We report benchmark results collected from the literature and find that they are not evaluated in a unified manner, making it difficult to compare and analyze. We thus built a unified benchmark framework to obtain directly comparable results on benchmark datasets. Furthermore, we evaluate relevant backbone networks pre-trained on ImageNet using our framework, providing an overview of the base corruption robustness of existing models to help choose appropriate backbones for computer vision tasks. We identify that developing methods to handle a wide range of corruptions and efficiently learn with limited data and computational resources is crucial for future development. Additionally, we highlight the need for further investigation into the relationship among corruption robustness, OOD generalization, and shortcut learning.

Abstract: The first MRI scan was done in the year 1978 by researchers at EML Laboratories. As per an estimate, approximately 251,329 people died due to primary cancerous brain and CNS (Central Nervous System) Tumors in the year 2020. It has been recommended by various medical professionals that brain tumor detection at an early stage would help in saving many lives. Whenever radiologists deal with a brain MRI they try to diagnose it with the histological subtype which is quite subjective and here comes the major issue. Upon that, in developing countries like India, where there is 1 doctor for every 1151 people, the need for efficient diagnosis to help radiologists and doctors come into picture. In our approach, we aim to solve the problem using swin transformers and deep learning to detect, classify, locate and provide the size of the tumor in the particular MRI scan which would assist the doctors and radiologists in increasing their efficiency. At the end, the medics would be able to download the predictions and measures in a PDF (Portable Document Format). Keywords: brain tumor, transformers, classification, medical, deep learning, detection

Abstract: Multi-view stereo depth estimation based on cost volume usually works better than self-supervised monocular depth estimation except for moving objects and low-textured surfaces. So in this paper, we propose a multi-frame depth estimation framework which monocular depth can be refined continuously by multi-frame sequential constraints, leveraging a Bayesian fusion layer within several iterations. Both monocular and multi-view networks can be trained with no depth supervision. Our method also enhances the interpretability when combining monocular estimation with multi-view cost volume. Detailed experiments show that our method surpasses state-of-the-art unsupervised methods utilizing single or multiple frames at test time on KITTI benchmark.

Abstract: Spontaneous retinal Venous Pulsations (SVP) are rhythmic changes in the caliber of the central retinal vein and are observed in the optic disc region (ODR) of the retina. Its absence is a critical indicator of various ocular or neurological abnormalities. Recent advances in imaging technology have enabled the development of portable smartphone-based devices for observing the retina and assessment of SVPs. However, the quality of smartphone-based retinal videos is often poor due to noise and image jitting, which in return, can severely obstruct the observation of SVPs. In this work, we developed a fully automated retinal video stabilization method that enables the examination of SVPs captured by various mobile devices. Specifically, we first propose an ODR Spatio-Temporal Localization (ODR-STL) module to localize visible ODR and remove noisy and jittering frames. Then, we introduce a Noise-Aware Template Matching (NATM) module to stabilize high-quality video segments at a fixed position in the field of view. After the processing, the SVPs can be easily observed in the stabilized videos, significantly facilitating user observations. Furthermore, our method is cost-effective and has been tested in both subjective and objective evaluations. Both of the evaluations support its effectiveness in facilitating the observation of SVPs. This can improve the timely diagnosis and treatment of associated diseases, making it a valuable tool for eye health professionals.

Abstract: Quantization is a widely adopted technique for deep neural networks to reduce the memory and computational resources required. However, when quantized, most models would need a suitable calibration process to keep their performance intact, which requires data from the target domain, such as a fraction of the dataset used in model training and model validation (i.e. calibration dataset). In this study, we investigate the use of synthetic data as a substitute for the calibration with real data for the quantization method. We propose a data generation method based on Generative Adversarial Networks that are trained prior to the model quantization step. We compare the performance of models quantized using data generated by StyleGAN2-ADA and our pre-trained DiStyleGAN, with quantization using real data and an alternative data generation method based on fractal images. Overall, the results of our experiments demonstrate the potential of leveraging synthetic data for calibration during the quantization process. In our experiments, the percentage of accuracy degradation of the selected models was less than 0.6%, with our best performance achieved on MobileNetV2 (0.05%). The code is available at: https://github.com/ThanosM97/gsoc2022-openvino

Abstract: Fine-tuning visual models has been widely shown promising performance on many downstream visual tasks. With the surprising development of pre-trained visual foundation models, visual tuning jumped out of the standard modus operandi that fine-tunes the whole pre-trained model or just the fully connected layer. Instead, recent advances can achieve superior performance than full-tuning the whole pre-trained parameters by updating far fewer parameters, enabling edge devices and downstream applications to reuse the increasingly large foundation models deployed on the cloud. With the aim of helping researchers get the full picture and future directions of visual tuning, this survey characterizes a large and thoughtful selection of recent works, providing a systematic and comprehensive overview of existing work and models. Specifically, it provides a detailed background of visual tuning and categorizes recent visual tuning techniques into five groups: prompt tuning, adapter tuning, parameter tuning, and remapping tuning. Meanwhile, it offers some exciting research directions for prospective pre-training and various interactions in visual tuning.

Abstract: Following the remarkable success of diffusion models on image generation, recent works have also demonstrated their impressive ability to address a number of inverse problems in an unsupervised way, by properly constraining the sampling process based on a conditioning input. Motivated by this, in this paper, we present the first approach to use diffusion models as a prior for highly accurate 3D facial BRDF reconstruction from a single image. We start by leveraging a high-quality UV dataset of facial reflectance (diffuse and specular albedo and normals), which we render under varying illumination settings to simulate natural RGB textures and, then, train an unconditional diffusion model on concatenated pairs of rendered textures and reflectance components. At test time, we fit a 3D morphable model to the given image and unwrap the face in a partial UV texture. By sampling from the diffusion model, while retaining the observed texture part intact, the model inpaints not only the self-occluded areas but also the unknown reflectance components, in a single sequence of denoising steps. In contrast to existing methods, we directly acquire the observed texture from the input image, thus, resulting in more faithful and consistent reflectance estimation. Through a series of qualitative and quantitative comparisons, we demonstrate superior performance in both texture completion as well as reflectance reconstruction tasks.

Abstract: Under partial-label learning (PLL) where, for each training instance, only a set of ambiguous candidate labels containing the unknown true label is accessible, contrastive learning has recently boosted the performance of PLL on vision tasks, attributed to representations learned by contrasting the same/different classes of entities. Without access to true labels, positive points are predicted using pseudo-labels that are inherently noisy, and negative points often require large batches or momentum encoders, resulting in unreliable similarity information and a high computational overhead. In this paper, we rethink a state-of-the-art contrastive PLL method PiCO[24], inspiring the design of a simple framework termed PaPi (Partial-label learning with a guided Prototypical classifier), which demonstrates significant scope for improvement in representation learning, thus contributing to label disambiguation. PaPi guides the optimization of a prototypical classifier by a linear classifier with which they share the same feature encoder, thus explicitly encouraging the representation to reflect visual similarity between categories. It is also technically appealing, as PaPi requires only a few components in PiCO with the opposite direction of guidance, and directly eliminates the contrastive learning module that would introduce noise and consume computational resources. We empirically demonstrate that PaPi significantly outperforms other PLL methods on various image classification tasks.

Abstract: This paper proposes a feedback mechanism to 'break bad habits' using the Pavlok device. Pavlok utilises beeps, vibration and shocks as a mode of aversion technique to help individuals with behaviour modification. While the device can be useful in certain periodic daily life situations, like alarms and exercise notifications, the device relies on manual operations that limit its usage. To this end, we design a user interface to generate an automatic feedback mechanism that integrates Pavlok and a deep learning based model to detect certain behaviours via an integrated user interface i.e. mobile or desktop application. Our proposed solution is implemented and verified in the context of snoring, which first detects audio from the environment following a prediction of whether the audio content is a snore or not. Based on the prediction of the deep learning model, we use Pavlok to alert users for preventive measures. We believe that this simple solution can help people to change their atomic habits, which may lead to long-term benefits.

Abstract: Current few-shot action recognition involves two primary sources of information for classification:(1) intra-video information, determined by frame content within a single video clip, and (2) inter-video information, measured by relationships (e.g., feature similarity) among videos. However, existing methods inadequately exploit these two information sources. In terms of intra-video information, current sampling operations for input videos may omit critical action information, reducing the utilization efficiency of video data. For the inter-video information, the action misalignment among videos makes it challenging to calculate precise relationships. Moreover, how to jointly consider both inter- and intra-video information remains under-explored for few-shot action recognition. To this end, we propose a novel framework, Video Information Maximization (VIM), for few-shot video action recognition. VIM is equipped with an adaptive spatial-temporal video sampler and a spatiotemporal action alignment model to maximize intra- and inter-video information, respectively. The video sampler adaptively selects important frames and amplifies critical spatial regions for each input video based on the task at hand. This preserves and emphasizes informative parts of video clips while eliminating interference at the data level. The alignment model performs temporal and spatial action alignment sequentially at the feature level, leading to more precise measurements of inter-video similarity. Finally, These goals are facilitated by incorporating additional loss terms based on mutual information measurement. Consequently, VIM acts to maximize the distinctiveness of video information from limited video data. Extensive experimental results on public datasets for few-shot action recognition demonstrate the effectiveness and benefits of our framework.

Abstract: Recently, Transformer-based methods for point cloud learning have achieved good results on various point cloud learning benchmarks. However, since the attention mechanism needs to generate three feature vectors of query, key, and value to calculate attention features, most of the existing Transformer-based point cloud learning methods usually consume a large amount of computational time and memory resources when calculating global attention. To address this problem, we propose a Voxel-Transformer-Point (VTP) Block for extracting local and global features of point clouds. VTP combines the advantages of voxel-based, point-based and Transformer-based methods, which consists of Voxel-Based Branch (V branch), Point-Based Transformer Branch (PT branch) and Point-Based Branch (P branch). The V branch extracts the coarse-grained features of the point cloud through low voxel resolution; the PT branch obtains the fine-grained features of the point cloud by calculating the self-attention in the local neighborhood and the inter-neighborhood cross-attention; the P branch uses a simplified MLP network to generate the global location information of the point cloud. In addition, to enrich the local features of point clouds at different scales, we set the voxel scale in the V branch and the neighborhood sphere scale in the PT branch to one large and one small (large voxel scale \& small neighborhood sphere scale or small voxel scale \& large neighborhood sphere scale). Finally, we use VTP as the feature extraction network to construct a VTPNet for point cloud learning, and performs shape classification, part segmentation, and semantic segmentation tasks on the ModelNet40, ShapeNet Part, and S3DIS datasets. The experimental results indicate that VTPNet has good performance in 3D point cloud learning.

Abstract: Estimating the camera pose given images of a single camera is a traditional task in mobile robots and autonomous vehicles. This problem is called monocular visual odometry and it often relies on geometric approaches that require engineering effort for a specific scenario. Deep learning methods have shown to be generalizable after proper training and a considerable amount of available data. Transformer-based architectures have dominated the state-of-the-art in natural language processing and computer vision tasks, such as image and video understanding. In this work, we deal with the monocular visual odometry as a video understanding task to estimate the 6-DoF camera's pose. We contribute by presenting the TSformer-VO model based on spatio-temporal self-attention mechanisms to extract features from clips and estimate the motions in an end-to-end manner. Our approach achieved competitive state-of-the-art performance compared with geometry-based and deep learning-based methods on the KITTI visual odometry dataset, outperforming the DeepVO implementation highly accepted in the visual odometry community.

Abstract: Generative AI (AIGC, a.k.a. AI generated content) has made remarkable progress in the past few years, among which text-guided content generation is the most practical one since it enables the interaction between human instruction and AIGC. Due to the development in text-to-image as well 3D modeling technologies (like NeRF), text-to-3D has become a newly emerging yet highly active research field. Our work conducts the first yet comprehensive survey on text-to-3D to help readers interested in this direction quickly catch up with its fast development. First, we introduce 3D data representations, including both Euclidean data and non-Euclidean data. On top of that, we introduce various foundation technologies as well as summarize how recent works combine those foundation technologies to realize satisfactory text-to-3D. Moreover, we summarize how text-to-3D technology is used in various applications, including avatar generation, texture generation, shape transformation, and scene generation.

Abstract: ChatGPT and its improved variant GPT4 have revolutionized the NLP field with a single model solving almost all text related tasks. However, such a model for computer vision does not exist, especially for 3D vision. This article first provides a brief view on the progress of deep learning in text, image and 3D fields from the model perspective. Moreover, this work further discusses how AIGC evolves from the data perspective. On top of that, this work presents an outlook on the development of AIGC in 3D from the data perspective.

Abstract: Semantic localization, i.e., robot self-localization with semantic image modality, is critical in recently emerging embodied AI applications such as point-goal navigation, object-goal navigation and vision language navigation. However, most existing works on semantic localization focus on passive vision tasks without viewpoint planning, or rely on additional rich modalities (e.g., depth measurements). Thus, the problem is largely unsolved. In this work, we explore a lightweight, entirely CPU-based, domain-adaptive semantic localization framework, called graph neural localizer.Our approach is inspired by two recently emerging technologies: (1) Scene graph, which combines the viewpoint- and appearance- invariance of local and global features; (2) Graph neural network, which enables direct learning/recognition of graph data (i.e., non-vector data). Specifically, a graph convolutional neural network is first trained as a scene graph classifier for passive vision, and then its knowledge is transferred to a reinforcement-learning planner for active vision. Experiments on two scenarios, self-supervised learning and unsupervised domain adaptation, using a photo-realistic Habitat simulator validate the effectiveness of the proposed method.

Abstract: In this paper, we address the problem of generalized category discovery (GCD), \ie, given a set of images where part of them are labelled and the rest are not, the task is to automatically cluster the images in the unlabelled data, leveraging the information from the labelled data, while the unlabelled data contain images from the labelled classes and also new ones. GCD is similar to semi-supervised learning (SSL) but is more realistic and challenging, as SSL assumes all the unlabelled images are from the same classes as the labelled ones. We also do not assume the class number in the unlabelled data is known a-priori, making the GCD problem even harder. To tackle the problem of GCD without knowing the class number, we propose an EM-like framework that alternates between representation learning and class number estimation. We propose a semi-supervised variant of the Gaussian Mixture Model (GMM) with a stochastic splitting and merging mechanism to dynamically determine the prototypes by examining the cluster compactness and separability. With these prototypes, we leverage prototypical contrastive learning for representation learning on the partially labelled data subject to the constraints imposed by the labelled data. Our framework alternates between these two steps until convergence. The cluster assignment for an unlabelled instance can then be retrieved by identifying its nearest prototype. We comprehensively evaluate our framework on both generic image classification datasets and challenging fine-grained object recognition datasets, achieving state-of-the-art performance.

Abstract: Clothes-invariant feature extraction is critical to the clothes-changing person re-identification (CC-ReID). It can provide discriminative identity features and eliminate the negative effects caused by the confounder--clothing changes. But we argue that there exists a strong spurious correlation between clothes and human identity, that restricts the common likelihood-based ReID method P(Y|X) to extract clothes-irrelevant features. In this paper, we propose a new Causal Clothes-Invariant Learning (CCIL) method to achieve clothes-invariant feature learning by modeling causal intervention P(Y|do(X)). This new causality-based model is inherently invariant to the confounder in the causal view, which can achieve the clothes-invariant features and avoid the barrier faced by the likelihood-based methods. Extensive experiments on three CC-ReID benchmarks, including PRCC, LTCC, and VC-Clothes, demonstrate the effectiveness of our approach, which achieves a new state of the art.

Abstract: Visual place classification from a first-person-view monocular RGB image is a fundamental problem in long-term robot navigation. A difficulty arises from the fact that RGB image classifiers are often vulnerable to spatial and appearance changes and degrade due to domain shifts, such as seasonal, weather, and lighting differences. To address this issue, multi-sensor fusion approaches combining RGB and depth (D) (e.g., LIDAR, radar, stereo) have gained popularity in recent years. Inspired by these efforts in multimodal RGB-D fusion, we explore the use of pseudo-depth measurements from recently-developed techniques of ``domain invariant" monocular depth estimation as an additional pseudo depth modality, by reformulating the single-modal RGB image classification task as a pseudo multi-modal RGB-D classification problem. Specifically, a practical, fully self-supervised framework for training, appropriately processing, fusing, and classifying these two modalities, RGB and pseudo-D, is described. Experiments on challenging cross-domain scenarios using public NCLT datasets validate effectiveness of the proposed framework.

Abstract: This paper aims for a new generation task: non-stationary multi-texture synthesis, which unifies synthesizing multiple non-stationary textures in a single model. Most non-stationary textures have large scale variance and can hardly be synthesized through one model. To combat this, we propose a multi-scale generator to capture structural patterns of various scales and effectively synthesize textures with a minor cost. However, it is still hard to handle textures of different categories with different texture patterns. Therefore, we present a category-specific training strategy to focus on learning texture pattern of a specific domain. Interestingly, once trained, our model is able to produce multi-pattern generations with dynamic variations without the need to finetune the model for different styles. Moreover, an objective evaluation metric is designed for evaluating the quality of texture expansion and global structure consistency. To our knowledge, ours is the first scheme for this challenging task, including model, training, and evaluation. Experimental results demonstrate the proposed method achieves superior performance and time efficiency. The code will be available after the publication.

Abstract: In recent years, soft prompt learning methods have been proposed to fine-tune large-scale vision-language pre-trained models for various downstream tasks. These methods typically combine learnable textual tokens with class tokens as input for models with frozen parameters. However, they often employ a single prompt to describe class contexts, failing to capture categories' diverse attributes adequately. This study introduces the Partitioned Multi-modal Prompt (PMPO), a multi-modal prompting technique that extends the soft prompt from a single learnable prompt to multiple prompts. Our method divides the visual encoder depths and connects learnable prompts to the separated visual depths, enabling different prompts to capture the hierarchical contextual depths of visual representations. Furthermore, to maximize the advantages of multi-prompt learning, we incorporate prior information from manually designed templates and learnable multi-prompts, thus improving the generalization capabilities of our approach. We evaluate the effectiveness of our approach on three challenging tasks: new class generalization, cross-dataset evaluation, and domain generalization. For instance, our method achieves a $79.28$ harmonic mean, averaged over 11 diverse image recognition datasets ($+7.62$ compared to CoOp), demonstrating significant competitiveness compared to state-of-the-art prompting methods.

Abstract: Predominant techniques on talking head generation largely depend on 2D information, including facial appearances and motions from input face images. Nevertheless, dense 3D facial geometry, such as pixel-wise depth, plays a critical role in constructing accurate 3D facial structures and suppressing complex background noises for generation. However, dense 3D annotations for facial videos is prohibitively costly to obtain. In this work, firstly, we present a novel self-supervised method for learning dense 3D facial geometry (ie, depth) from face videos, without requiring camera parameters and 3D geometry annotations in training. We further propose a strategy to learn pixel-level uncertainties to perceive more reliable rigid-motion pixels for geometry learning. Secondly, we design an effective geometry-guided facial keypoint estimation module, providing accurate keypoints for generating motion fields. Lastly, we develop a 3D-aware cross-modal (ie, appearance and depth) attention mechanism, which can be applied to each generation layer, to capture facial geometries in a coarse-to-fine manner. Extensive experiments are conducted on three challenging benchmarks (ie, VoxCeleb1, VoxCeleb2, and HDTF). The results demonstrate that our proposed framework can generate highly realistic-looking reenacted talking videos, with new state-of-the-art performances established on these benchmarks. The codes and trained models are publicly available on the GitHub project page at https://github.com/harlanhong/CVPR2022-DaGAN

Abstract: X-ray images are the first steps for diagnosing and further treating dental problems. So, early diagnosis prevents the development and increase of oral and dental diseases. In this paper, we developed a semantic segmentation algorithm based on BEIT adaptor and Mask2Former to detect and identify teeth, roots, and multiple dental diseases and abnormalities such as pulp chamber, restoration, endodontics, crown, decay, pin, composite, bridge, pulpitis, orthodontics, radicular cyst, periapical cyst, cyst, implant, and bone graft material in panoramic, periapical, and bitewing X-ray images. We compared the result of our algorithm to two state-of-the-art algorithms in image segmentation named: Deeplabv3 and Segformer on our own data set. We discovered that Radious outperformed those algorithms by increasing the mIoU scores by 9% and 33% in Deeplabv3+ and Segformer, respectively.

Abstract: End-to-end autonomous driving has made impressive progress in recent years. Existing methods usually adopt the decoupled encoder-decoder paradigm, where the encoder extracts hidden features from raw sensor data, and the decoder outputs the ego-vehicle's future trajectories or actions. Under such a paradigm, the encoder does not have access to the intended behavior of the ego agent, leaving the burden of finding out safety-critical regions from the massive receptive field and inferring about future situations to the decoder. Even worse, the decoder is usually composed of several simple multi-layer perceptrons (MLP) or GRUs while the encoder is delicately designed (e.g., a combination of heavy ResNets or Transformer). Such an imbalanced resource-task division hampers the learning process. In this work, we aim to alleviate the aforementioned problem by two principles: (1) fully utilizing the capacity of the encoder; (2) increasing the capacity of the decoder. Concretely, we first predict a coarse-grained future position and action based on the encoder features. Then, conditioned on the position and action, the future scene is imagined to check the ramification if we drive accordingly. We also retrieve the encoder features around the predicted coordinate to obtain fine-grained information about the safety-critical region. Finally, based on the predicted future and the retrieved salient feature, we refine the coarse-grained position and action by predicting its offset from ground-truth. The above refinement module could be stacked in a cascaded fashion, which extends the capacity of the decoder with spatial-temporal prior knowledge about the conditioned future. We conduct experiments on the CARLA simulator and achieve state-of-the-art performance in closed-loop benchmarks. Extensive ablation studies demonstrate the effectiveness of each proposed module.

Abstract: Automated multi-label chest X-rays (CXR) image classification has achieved substantial progress in clinical diagnosis via utilizing sophisticated deep learning approaches. However, most deep models have high computational demands, which makes them less feasible for compact devices with low computational requirements. To overcome this problem, we propose a knowledge distillation (KD) strategy to create the compact deep learning model for the real-time multi-label CXR image classification. We study different alternatives of CNNs and Transforms as the teacher to distill the knowledge to a smaller student. Then, we employed explainable artificial intelligence (XAI) to provide the visual explanation for the model decision improved by the KD. Our results on three benchmark CXR datasets show that our KD strategy provides the improved performance on the compact student model, thus being the feasible choice for many limited hardware platforms. For instance, when using DenseNet161 as the teacher network, EEEA-Net-C2 achieved an AUC of 83.7%, 87.1%, and 88.7% on the ChestX-ray14, CheXpert, and PadChest datasets, respectively, with fewer parameters of 4.7 million and computational cost of 0.3 billion FLOPS.

Abstract: We present a novel deep learning-based framework: Embedded Feature Correlation Optimization with Specific Parameter Initialization (COSPI) for 2D/3D registration which is a most challenging problem due to the difficulty such as dimensional mismatch, heavy computation load and lack of golden evaluating standard. The framework we designed includes a parameter specification module to efficiently choose initialization pose parameter and a fine-registration network to align images. The proposed framework takes extracting multi-scale features into consideration using a novel composite connection encoder with special training techniques. The method is compared with both learning-based methods and optimization-based methods to further evaluate the performance. Our experiments demonstrate that the method in this paper has improved the registration performance, and thereby outperforms the existing methods in terms of accuracy and running time. We also show the potential of the proposed method as an initial pose estimator.

Abstract: Recovering an outdoor environment's surface mesh is vital for an agricultural robot during task planning and remote visualization. Our proposed solution is based on a newly-designed panoramic stereo camera along with a hybrid novel software framework that consists of three fusion modules. The panoramic stereo camera with a pentagon shape consists of 5 stereo vision camera pairs to stream synchronized panoramic stereo images for the following three fusion modules. In the disparity fusion module, rectified stereo images produce the initial disparity maps using multiple stereo vision algorithms. Then, these initial disparity maps, along with the intensity images, are input into a disparity fusion network to produce refined disparity maps. Next, the refined disparity maps are converted into full-view point clouds or single-view point clouds for the pose fusion module. The pose fusion module adopts a two-stage global-coarse-to-local-fine strategy. In the first stage, each pair of full-view point clouds is registered by a global point cloud matching algorithm to estimate the transformation for a global pose graph's edge, which effectively implements loop closure. In the second stage, a local point cloud matching algorithm is used to match single-view point clouds in different nodes. Next, we locally refine the poses of all corresponding edges in the global pose graph using three proposed rules, thus constructing a refined pose graph. The refined pose graph is optimized to produce a global pose trajectory for volumetric fusion. In the volumetric fusion module, the global poses of all the nodes are used to integrate the single-view point clouds into the volume to produce the mesh of the whole garden. The proposed framework and its three fusion modules are tested on a real outdoor garden dataset to show the superiority of the performance.

Abstract: Instance segmentation is a fundamental skill for many robotic applications. We propose a self-supervised method that uses grasp interactions to collect segmentation supervision for an instance segmentation model. When a robot grasps an item, the mask of that grasped item can be inferred from the images of the scene before and after the grasp. Leveraging this insight, we learn a grasp segmentation model to segment the grasped object from before and after grasp images. Such a model can segment grasped objects from thousands of grasp interactions without costly human annotation. Using the segmented grasped objects, we can "cut" objects from their original scenes and "paste" them into new scenes to generate instance supervision. We show that our grasp segmentation model provides a 5x error reduction when segmenting grasped objects compared with traditional image subtraction approaches. Combined with our "cut-and-paste" generation method, instance segmentation models trained with our method achieve better performance than a model trained with 10x the amount of labeled data. On a real robotic grasping system, our instance segmentation model reduces the rate of grasp errors by over 3x compared to an image subtraction baseline.

Abstract: As virtual and physical identity grow increasingly intertwined, the importance of privacy and security in the online sphere becomes paramount. In recent years, multiple news stories have emerged of private companies scraping web content and doing research with or selling the data. Images uploaded online can be scraped without users' consent or knowledge. Users of social media platforms whose images are scraped may be at risk of being identified in other uploaded images or in real-world identification situations. This paper investigates how simple, accessible image manipulation techniques affect the accuracy of facial recognition software in identifying an individual's various face images based on one unique image.

Abstract: Reconstructing semantic 3D building models at the level of detail (LoD) 3 is a long-standing challenge. Unlike mesh-based models, they require watertight geometry and object-wise semantics at the fa\c{c}ade level. The principal challenge of such demanding semantic 3D reconstruction is reliable fa\c{c}ade-level semantic segmentation of 3D input data. We present a novel method, called Scan2LoD3, that accurately reconstructs semantic LoD3 building models by improving fa\c{c}ade-level semantic 3D segmentation. To this end, we leverage laser physics and 3D building model priors to probabilistically identify model conflicts. These probabilistic physical conflicts propose locations of model openings: Their final semantics and shapes are inferred in a Bayesian network fusing multimodal probabilistic maps of conflicts, 3D point clouds, and 2D images. To fulfill demanding LoD3 requirements, we use the estimated shapes to cut openings in 3D building priors and fit semantic 3D objects from a library of fa\c{c}ade objects. Extensive experiments on the TUM city campus datasets demonstrate the superior performance of the proposed Scan2LoD3 over the state-of-the-art methods in fa\c{c}ade-level detection, semantic segmentation, and LoD3 building model reconstruction. We believe our method can foster the development of probability-driven semantic 3D reconstruction at LoD3 since not only the high-definition reconstruction but also reconstruction confidence becomes pivotal for various applications such as autonomous driving and urban simulations.

Abstract: Malicious Deepfakes have led to a sharp conflict over distinguishing between genuine and forged faces. Although many countermeasures have been developed to detect Deepfakes ex-post, undoubtedly, passive forensics has not considered any preventive measures for the pristine face before foreseeable manipulations. To complete this forensics ecosystem, we thus put forward the proactive solution dubbed SepMark, which provides a unified framework for source tracing and Deepfake detection. SepMark originates from encoder-decoder-based deep watermarking but with two separable decoders. For the first time the deep separable watermarking, SepMark brings a new paradigm to the established study of deep watermarking, where a single encoder embeds one watermark elegantly, while two decoders can extract the watermark separately at different levels of robustness. The robust decoder termed Tracer that resists various distortions may have an overly high level of robustness, allowing the watermark to survive both before and after Deepfake. The semi-robust one termed Detector is selectively sensitive to malicious distortions, making the watermark disappear after Deepfake. Only SepMark comprising of Tracer and Detector can reliably trace the trusted source of the marked face and detect whether it has been altered since being marked; neither of the two alone can achieve this. Extensive experiments demonstrate the effectiveness of the proposed SepMark on typical Deepfakes, including face swapping, expression reenactment, and attribute editing.

Abstract: We present Integrated Multimodal Perception (IMP), a simple and scalable multimodal multi-task training and modeling approach. IMP integrates multimodal inputs including image, video, text, and audio into a single Transformer encoder with minimal modality-specific components. IMP makes use of a novel design that combines Alternating Gradient Descent (AGD) and Mixture-of-Experts (MoE) for efficient model \& task scaling. We conduct extensive empirical studies about IMP and reveal the following key insights: 1) performing gradient descent updates by alternating on diverse heterogeneous modalities, loss functions, and tasks, while also varying input resolutions, efficiently improves multimodal understanding. 2) model sparsification with MoE on a single modality-agnostic encoder substantially improves the performance, outperforming dense models that use modality-specific encoders or additional fusion layers and greatly mitigating the conflicts between modalities. IMP achieves competitive performance on a wide range of downstream tasks including image classification, video classification, image-text, and video-text retrieval. Most notably, we train a sparse IMP-MoE-L focusing on video tasks that achieves new state-of-the-art in zero-shot video classification. Our model achieves 77.0% on Kinetics-400, 76.8% on Kinetics-600, and 76.8% on Kinetics-700 zero-shot classification accuracy, improving the previous state-of-the-art by +5%, +6.7%, and +5.8%, respectively, while using only 15% of their total training computational cost.

Abstract: Vision and Language (VL) models have demonstrated remarkable zero-shot performance in a variety of tasks. However, recent studies have shown that even the best VL models struggle to capture aspects of scene understanding, such as object attributes, relationships, and action states. In contrast, obtaining structured annotations, e.g., scene graphs (SGs) that could improve these models is time-consuming, costly, and tedious, and thus cannot be used on a large scale. Here we ask, can small datasets containing SG annotations provide sufficient information for enhancing structured understanding of VL models? We show that it is indeed possible to improve VL models using such data by utilizing a specialized model architecture and a new training paradigm. Our approach captures structure-related information for both the visual and textual encoders by directly supervising both components when learning from SG labels. We use scene graph supervision to generate fine-grained captions based on various graph augmentations highlighting different compositional aspects of the scene, and to predict SG information using an open vocabulary approach by adding special ``Adaptive SG tokens'' to the visual encoder. Moreover, we design a new adaptation technique tailored specifically to the SG tokens that allows better learning of the graph prediction task while still maintaining zero-shot capabilities. Our model shows strong performance improvements on the Winoground and VL-checklist datasets with only a mild degradation in zero-shot performance.

Abstract: Building animatable 3D models is challenging due to the need for 3D scans, laborious registration, and manual rigging, which are difficult to scale to arbitrary categories. Recently, differentiable rendering provides a pathway to obtain high-quality 3D models from monocular videos, but these are limited to rigid categories or single instances. We present RAC that builds category 3D models from monocular videos while disentangling variations over instances and motion over time. Three key ideas are introduced to solve this problem: (1) specializing a skeleton to instances via optimization, (2) a method for latent space regularization that encourages shared structure across a category while maintaining instance details, and (3) using 3D background models to disentangle objects from the background. We show that 3D models of humans, cats, and dogs can be learned from 50-100 internet videos.

Abstract: In this study, we initiate an exploration into video understanding by introducing VideoChat, an end-to-end chat-centric video understanding system. It integrates video foundation models and large language models via a learnable neural interface, excelling in spatiotemporal reasoning, event localization, and causal relationship inference. To instructively tune this system, we propose a video-centric instruction dataset, composed of thousands of videos matched with detailed descriptions and conversations. This dataset emphasizes spatiotemporal reasoning and causal relationships, providing a valuable asset for training chat-centric video understanding systems. Preliminary qualitative experiments reveal our system's potential across a broad spectrum of video applications and set the standard for future research. Access our code and data at https://github.com/OpenGVLab/Ask-Anything

Abstract: Representing human performance at high-fidelity is an essential building block in diverse applications, such as film production, computer games or videoconferencing. To close the gap to production-level quality, we introduce HumanRF, a 4D dynamic neural scene representation that captures full-body appearance in motion from multi-view video input, and enables playback from novel, unseen viewpoints. Our novel representation acts as a dynamic video encoding that captures fine details at high compression rates by factorizing space-time into a temporal matrix-vector decomposition. This allows us to obtain temporally coherent reconstructions of human actors for long sequences, while representing high-resolution details even in the context of challenging motion. While most research focuses on synthesizing at resolutions of 4MP or lower, we address the challenge of operating at 12MP. To this end, we introduce ActorsHQ, a novel multi-view dataset that provides 12MP footage from 160 cameras for 16 sequences with high-fidelity, per-frame mesh reconstructions. We demonstrate challenges that emerge from using such high-resolution data and show that our newly introduced HumanRF effectively leverages this data, making a significant step towards production-level quality novel view synthesis.