Computer Vision and Pattern Recognition (cs.CV)

Abstract: This paper introduces the novel concept of few-shot weakly supervised learning for pathology Whole Slide Image (WSI) classification, denoted as FSWC. A solution is proposed based on prompt learning and the utilization of a large language model, GPT-4. Since a WSI is too large and needs to be divided into patches for processing, WSI classification is commonly approached as a Multiple Instance Learning (MIL) problem. In this context, each WSI is considered a bag, and the obtained patches are treated as instances. The objective of FSWC is to classify both bags and instances with only a limited number of labeled bags. Unlike conventional few-shot learning problems, FSWC poses additional challenges due to its weak bag labels within the MIL framework. Drawing inspiration from the recent achievements of vision-language models (V-L models) in downstream few-shot classification tasks, we propose a two-level prompt learning MIL framework tailored for pathology, incorporating language prior knowledge. Specifically, we leverage CLIP to extract instance features for each patch, and introduce a prompt-guided pooling strategy to aggregate these instance features into a bag feature. Subsequently, we employ a small number of labeled bags to facilitate few-shot prompt learning based on the bag features. Our approach incorporates the utilization of GPT-4 in a question-and-answer mode to obtain language prior knowledge at both the instance and bag levels, which are then integrated into the instance and bag level language prompts. Additionally, a learnable component of the language prompts is trained using the available few-shot labeled data. We conduct extensive experiments on three real WSI datasets encompassing breast cancer, lung cancer, and cervical cancer, demonstrating the notable performance of the proposed method in bag and instance classification. All codes will be made publicly accessible.

Abstract: Because of the ambiguous and subjective property of the facial expression recognition (FER) task, the label noise is widely existing in the FER dataset. For this problem, in the training phase, current FER methods often directly predict whether the label of the input image is noised or not, aiming to reduce the contribution of the noised data in training. However, we argue that this kind of method suffers from the low reliability of such noise data decision operation. It makes that some mistakenly abounded clean data are not utilized sufficiently and some mistakenly kept noised data disturbing the model learning process. In this paper, we propose a more reliable noise-label suppression method called ReSup (Reliable label noise Suppression for FER). First, instead of directly predicting noised or not, ReSup makes the noise data decision by modeling the distribution of noise and clean labels simultaneously according to the disagreement between the prediction and the target. Specifically, to achieve optimal distribution modeling, ReSup models the similarity distribution of all samples. To further enhance the reliability of our noise decision results, ReSup uses two networks to jointly achieve noise suppression. Specifically, ReSup utilize the property that two networks are less likely to make the same mistakes, making two networks swap decisions and tending to trust decisions with high agreement. Extensive experiments on three popular benchmarks show that the proposed method significantly outperforms state-of-the-art noisy label FER methods by 3.01% on FERPlus becnmarks. Code: https://github.com/purpleleaves007/FERDenoise

Abstract: Magnetic resonance imaging (MRI) is a valuable clinical tool for displaying anatomical structures and aiding in accurate diagnosis. Medical image super-resolution (SR) reconstruction using deep learning techniques can enhance lesion analysis and assist doctors in improving diagnostic efficiency and accuracy. However, existing deep learning-based SR methods predominantly rely on convolutional neural networks (CNNs), which inherently limit the expressive capabilities of these models and therefore make it challenging to discover potential relationships between different image features. To overcome this limitation, we propose an A-network that utilizes multiple convolution operator feature extraction modules (MCO) for extracting image features using multiple convolution operators. These extracted features are passed through multiple sets of cross-feature extraction modules (MSC) to highlight key features through inter-channel feature interactions, enabling subsequent feature learning. An attention-based sparse graph neural network module is incorporated to establish relationships between pixel features, learning which adjacent pixels have the greatest impact on determining the features to be filled. To evaluate our model's effectiveness, we conducted experiments using different models on data generated from multiple datasets with different degradation multiples, and the experimental results show that our method is a significant improvement over the current state-of-the-art methods.

Abstract: Recent advancements in multimodal foundation models (e.g., CLIP) have excelled in zero-shot generalization. Prompt tuning involved in the knowledge transfer from foundation models to downstream tasks has gained significant attention recently. Existing prompt-tuning methods in cross-modal learning, however, either solely focus on language branch, or learn vision-language interaction in a shallow mechanism. In this context, we propose a Deeply coupled Cross-modal Prompt learning (DCP) method based on CLIP. DCP flexibly accommodates the interplay between vision and language with a Cross-Modal Prompt Attention (CMPA) mechanism, which enables the mutual exchange of respective representation through a well-connected multi-head attention module progressively and strongly. We then conduct comprehensive few-shot learning experiments on 11 image classification datasets and analyze the robustness to domain shift as well. Thorough experimental analysis evidently demonstrates the superb few-shot generalization and compelling domain adaption capacity of a well-executed DCP. The code can be found at https://github.com/GingL/CMPA.

Abstract: Neural radiance fields (NeRFs) are able to synthesize realistic novel views from multi-view images captured from distinct positions and perspectives. In NeRF's rendering pipeline, neural networks are used to represent a scene independently or transform queried learnable feature vector of a point to the expected color or density. With the aid of geometry guides either in occupancy grids or proposal networks, the number of neural network evaluations can be reduced from hundreds to dozens in the standard volume rendering framework. Instead of rendering yielded color after neural network evaluation, we propose to render the queried feature vectors of a ray first and then transform the rendered feature vector to the final pixel color by a neural network. This fundamental change to the standard volume rendering framework requires only one single neural network evaluation to render a pixel, which substantially lowers the high computational complexity of the rendering framework attributed to a large number of neural network evaluations. Consequently, we can use a comparably larger neural network to achieve a better rendering quality while maintaining the same training and rendering time costs. Our model achieves the state-of-the-art rendering quality on both synthetic and real-world datasets while requiring a training time of several minutes.

Abstract: Currently, object detection applications in construction are almost based on pure 2D data (both image and annotation are 2D-based), resulting in the developed artificial intelligence (AI) applications only applicable to some scenarios that only require 2D information. However, most advanced applications usually require AI agents to perceive 3D spatial information, which limits the further development of the current computer vision (CV) in construction. The lack of 3D annotated datasets for construction object detection worsens the situation. Therefore, this study creates and releases a virtual dataset with 3D annotations named VCVW-3D, which covers 15 construction scenes and involves ten categories of construction vehicles and workers. The VCVW-3D dataset is characterized by multi-scene, multi-category, multi-randomness, multi-viewpoint, multi-annotation, and binocular vision. Several typical 2D and monocular 3D object detection models are then trained and evaluated on the VCVW-3D dataset to provide a benchmark for subsequent research. The VCVW-3D is expected to bring considerable economic benefits and practical significance by reducing the costs of data construction, prototype development, and exploration of space-awareness applications, thus promoting the development of CV in construction, especially those of 3D applications.

Abstract: We develop a method that recovers the surface, materials, and illumination of a scene from its posed multi-view images. In contrast to prior work, it does not require any additional data and can handle glossy objects or bright lighting. It is a progressive inverse rendering approach, which consists of three stages. First, we reconstruct the scene radiance and signed distance function (SDF) with our novel regularization strategy for specular reflections. Our approach considers both the diffuse and specular colors, which allows for handling complex view-dependent lighting effects for surface reconstruction. Second, we distill light visibility and indirect illumination from the learned SDF and radiance field using learnable mapping functions. Third, we design a method for estimating the ratio of incoming direct light represented via Spherical Gaussians reflected in a specular manner and then reconstruct the materials and direct illumination of the scene. Experimental results demonstrate that the proposed method outperforms the current state-of-the-art in recovering surfaces, materials, and lighting without relying on any additional data.

Abstract: Accident of struck-by machines is one of the leading causes of casualties on construction sites. Monitoring workers' proximities to avoid human-machine collisions has aroused great concern in construction safety management. Existing methods are either too laborious and costly to apply extensively, or lacking spatial perception for accurate monitoring. Therefore, this study proposes a novel framework for proximity monitoring using only an ordinary 2D camera to realize real-time human-machine collision warning, which is designed to integrate a monocular 3D object detection model to perceive spatial information from 2D images and a post-processing classification module to identify the proximity as four predefined categories: Dangerous, Potentially Dangerous, Concerned, and Safe. A virtual dataset containing 22000 images with 3D annotations is constructed and publicly released to facilitate the system development and evaluation. Experimental results show that the trained 3D object detection model achieves 75% loose AP within 20 meters. Besides, the implemented system is real-time and camera carrier-independent, achieving an F1 of roughly 0.8 within 50 meters under specified settings for machines of different sizes. This study preliminarily reveals the potential and feasibility of proximity monitoring using only a 2D camera, providing a new promising and economical way for early warning of human-machine collisions.

Abstract: Camouflaged Object Detection (COD) is a challenging task in computer vision due to the high similarity between camouflaged objects and their surroundings. Existing COD methods primarily employ semantic segmentation, which suffers from overconfident incorrect predictions. In this paper, we propose a new paradigm that treats COD as a conditional mask-generation task leveraging diffusion models. Our method, dubbed CamoDiffusion, employs the denoising process of diffusion models to iteratively reduce the noise of the mask. Due to the stochastic sampling process of diffusion, our model is capable of sampling multiple possible predictions from the mask distribution, avoiding the problem of overconfident point estimation. Moreover, we develop specialized learning strategies that include an innovative ensemble approach for generating robust predictions and tailored forward diffusion methods for efficient training, specifically for the COD task. Extensive experiments on three COD datasets attest the superior performance of our model compared to existing state-of-the-art methods, particularly on the most challenging COD10K dataset, where our approach achieves 0.019 in terms of MAE.

Abstract: Most existing learning-based pose estimation methods are typically developed for non-zero-shot scenarios, where they can only estimate the poses of objects present in the training dataset. This setting restricts their applicability to unseen objects in the training phase. In this paper, we introduce a fully zero-shot pose estimation pipeline that leverages the 3D models of objects as clues. Specifically, we design a two-step pipeline consisting of 3D model-based zero-shot instance segmentation and a zero-shot pose estimator. For the first step, there is a novel way to perform zero-shot instance segmentation based on the 3D models instead of text descriptions, which can handle complex properties of unseen objects. For the second step, we utilize a hierarchical geometric structure matching mechanism to perform zero-shot pose estimation which is 10 times faster than the current render-based method. Extensive experimental results on the seven core datasets on the BOP challenge show that the proposed method outperforms the zero-shot state-of-the-art method with higher speed and lower computation cost.

Abstract: Using Fourier analysis, we explore the robustness and vulnerability of graph convolutional neural networks (GCNs) for skeleton-based action recognition. We adopt a joint Fourier transform (JFT), a combination of the graph Fourier transform (GFT) and the discrete Fourier transform (DFT), to examine the robustness of adversarially-trained GCNs against adversarial attacks and common corruptions. Experimental results with the NTU RGB+D dataset reveal that adversarial training does not introduce a robustness trade-off between adversarial attacks and low-frequency perturbations, which typically occurs during image classification based on convolutional neural networks. This finding indicates that adversarial training is a practical approach to enhancing robustness against adversarial attacks and common corruptions in skeleton-based action recognition. Furthermore, we find that the Fourier approach cannot explain vulnerability against skeletal part occlusion corruption, which highlights its limitations. These findings extend our understanding of the robustness of GCNs, potentially guiding the development of more robust learning methods for skeleton-based action recognition.

Abstract: Compositional Zero-Shot Learning (CZSL) aims to train models to recognize novel compositional concepts based on learned concepts such as attribute-object combinations. One of the challenges is to model attributes interacted with different objects, e.g., the attribute ``wet" in ``wet apple" and ``wet cat" is different. As a solution, we provide analysis and argue that attributes are conditioned on the recognized object and input image and explore learning conditional attribute embeddings by a proposed attribute learning framework containing an attribute hyper learner and an attribute base learner. By encoding conditional attributes, our model enables to generate flexible attribute embeddings for generalization from seen to unseen compositions. Experiments on CZSL benchmarks, including the more challenging C-GQA dataset, demonstrate better performances compared with other state-of-the-art approaches and validate the importance of learning conditional attributes. Code is available at https://github.com/wqshmzh/CANet-CZSL

Abstract: For autonomous vehicles, driving safely is highly dependent on the capability to correctly perceive the environment in 3D space, hence the task of 3D object detection represents a fundamental aspect of perception. While 3D sensors deliver accurate metric perception, monocular approaches enjoy cost and availability advantages that are valuable in a wide range of applications. Unfortunately, training monocular methods requires a vast amount of annotated data. Interestingly, self-supervised approaches have recently been successfully applied to ease the training process and unlock access to widely available unlabelled data. While related research leverages different priors including LIDAR scans and stereo images, such priors again limit usability. Therefore, in this work, we propose a novel approach to self-supervise 3D object detection purely from RGB sequences alone, leveraging multi-view constraints and weak labels. Our experiments on KITTI 3D dataset demonstrate performance on par with state-of-the-art self-supervised methods using LIDAR scans or stereo images.

Abstract: Automated assembly of 3D fractures is essential in orthopedics, archaeology, and our daily life. This paper presents Jigsaw, a novel framework for assembling physically broken 3D objects from multiple pieces. Our approach leverages hierarchical features of global and local geometry to match and align the fracture surfaces. Our framework consists of three components: (1) surface segmentation to separate fracture and original parts, (2) multi-parts matching to find correspondences among fracture surface points, and (3) robust global alignment to recover the global poses of the pieces. We show how to jointly learn segmentation and matching and seamlessly integrate feature matching and rigidity constraints. We evaluate Jigsaw on the Breaking Bad dataset and achieve superior performance compared to state-of-the-art methods. Our method also generalizes well to diverse fracture modes, objects, and unseen instances. To the best of our knowledge, this is the first learning-based method designed specifically for 3D fracture assembly over multiple pieces.

Abstract: Token compression aims to speed up large-scale vision transformers (e.g. ViTs) by pruning (dropping) or merging tokens. It is an important but challenging task. Although recent advanced approaches achieved great success, they need to carefully handcraft a compression rate (i.e. number of tokens to remove), which is tedious and leads to sub-optimal performance. To tackle this problem, we propose Differentiable Compression Rate (DiffRate), a novel token compression method that has several appealing properties prior arts do not have. First, DiffRate enables propagating the loss function's gradient onto the compression ratio, which is considered as a non-differentiable hyperparameter in previous work. In this case, different layers can automatically learn different compression rates layer-wisely without extra overhead. Second, token pruning and merging can be naturally performed simultaneously in DiffRate, while they were isolated in previous works. Third, extensive experiments demonstrate that DiffRate achieves state-of-the-art performance. For example, by applying the learned layer-wise compression rates to an off-the-shelf ViT-H (MAE) model, we achieve a 40% FLOPs reduction and a 1.5x throughput improvement, with a minor accuracy drop of 0.16% on ImageNet without fine-tuning, even outperforming previous methods with fine-tuning. Codes and models are available at https://github.com/OpenGVLab/DiffRate.

Abstract: We present a novel algorithm for text-driven image-to-image translation based on a pretrained text-to-image diffusion model. Our method aims to generate a target image by selectively editing the regions of interest in a source image, defined by a modifying text, while preserving the remaining parts. In contrast to existing techniques that solely rely on a target prompt, we introduce a new score function, which considers both a source prompt and a source image, tailored to address specific translation tasks. To this end, we derive the conditional score function in a principled manner, decomposing it into a standard score and a guiding term for target image generation. For the gradient computation, we adopt a Gaussian distribution of the posterior distribution, estimating its mean and variance without requiring additional training. In addition, to enhance the conditional score guidance, we incorporate a simple yet effective mixup method. This method combines two cross-attention maps derived from the source and target latents, promoting the generation of the target image by a desirable fusion of the original parts in the source image and the edited regions aligned with the target prompt. Through comprehensive experiments, we demonstrate that our approach achieves outstanding image-to-image translation performance on various tasks.

Abstract: Despite the dynamic development of computer vision algorithms, the implementation of perception and control systems for autonomous vehicles such as drones and self-driving cars still poses many challenges. A video stream captured by traditional cameras is often prone to problems such as motion blur or degraded image quality due to challenging lighting conditions. In addition, the frame rate - typically 30 or 60 frames per second - can be a limiting factor in certain scenarios. Event cameras (DVS -- Dynamic Vision Sensor) are a potentially interesting technology to address the above mentioned problems. In this paper, we compare two methods of processing event data by means of deep learning for the task of pedestrian detection. We used a representation in the form of video frames, convolutional neural networks and asynchronous sparse convolutional neural networks. The results obtained illustrate the potential of event cameras and allow the evaluation of the accuracy and efficiency of the methods used for high-resolution (1280 x 720 pixels) footage.

Abstract: In this work, we introduce a new approach for artistic face stylization. Despite existing methods achieving impressive results in this task, there is still room for improvement in generating high-quality stylized faces with diverse styles and accurate facial reconstruction. Our proposed framework, MMFS, supports multi-modal face stylization by leveraging the strengths of StyleGAN and integrates it into an encoder-decoder architecture. Specifically, we use the mid-resolution and high-resolution layers of StyleGAN as the decoder to generate high-quality faces, while aligning its low-resolution layer with the encoder to extract and preserve input facial details. We also introduce a two-stage training strategy, where we train the encoder in the first stage to align the feature maps with StyleGAN and enable a faithful reconstruction of input faces. In the second stage, the entire network is fine-tuned with artistic data for stylized face generation. To enable the fine-tuned model to be applied in zero-shot and one-shot stylization tasks, we train an additional mapping network from the large-scale Contrastive-Language-Image-Pre-training (CLIP) space to a latent $w+$ space of fine-tuned StyleGAN. Qualitative and quantitative experiments show that our framework achieves superior face stylization performance in both one-shot and zero-shot stylization tasks, outperforming state-of-the-art methods by a large margin.

Abstract: Misalignment between the outputs of a vision-language (VL) model and task goal hinders its deployment. This issue can worsen when there are distribution shifts between the training and test data. To address this problem, prevailing fully test-time adaptation~(TTA) methods bootstrap themselves through entropy minimization. However, minimizing the entropy of the predictions makes the model overfit to incorrect output distributions of itself. In this work, we propose TTA with feedback to avoid such overfitting and align the model with task goals. Specifically, we adopt CLIP as reward model to provide feedback for VL models during test time in various tasks, including image classification, image-text retrieval, and image captioning. Given a single test sample, the model aims to maximize CLIP reward through reinforcement learning. We adopt a reward design with the average CLIP score of sampled candidates as the baseline. This design is simple and surprisingly effective when combined with various task-specific sampling strategies. The entire system is flexible, allowing the reward model to be extended with multiple CLIP models. Plus, a momentum buffer can be used to memorize and leverage the learned knowledge from multiple test samples. Extensive experiments demonstrate that our method significantly improves different VL models after TTA.

Abstract: Foreground segmentation is a fundamental problem in computer vision, which includes salient object detection, forgery detection, defocus blur detection, shadow detection, and camouflage object detection. Previous works have typically relied on domain-specific solutions to address accuracy and robustness issues in those applications. In this paper, we present a unified framework for a number of foreground segmentation tasks without any task-specific designs. We take inspiration from the widely-used pre-training and then prompt tuning protocols in NLP and propose a new visual prompting model, named Explicit Visual Prompting (EVP). Different from the previous visual prompting which is typically a dataset-level implicit embedding, our key insight is to enforce the tunable parameters focusing on the explicit visual content from each individual image, i.e., the features from frozen patch embeddings and high-frequency components. Our method freezes a pre-trained model and then learns task-specific knowledge using a few extra parameters. Despite introducing only a small number of tunable parameters, EVP achieves superior performance than full fine-tuning and other parameter-efficient fine-tuning methods. Experiments in fourteen datasets across five tasks show the proposed method outperforms other task-specific methods while being considerably simple. The proposed method demonstrates the scalability in different architectures, pre-trained weights, and tasks. The code is available at: https://github.com/NiFangBaAGe/Explicit-Visual-Prompt.

Abstract: Autonomous driving systems often require reliable loop closure detection to guarantee reduced localization drift. Recently, 3D LiDAR-based localization methods have used retrieval-based place recognition to find revisited places efficiently. However, when deployed in challenging real-world scenarios, the place recognition models become more complex, which comes at the cost of high computational demand. This work tackles this problem from an information-retrieval perspective, adopting a first-retrieve-then-re-ranking paradigm, where an initial loop candidate ranking, generated from a 3D place recognition model, is re-ordered by a proposed lightweight transformer-based re-ranking approach (TReR). The proposed approach relies on global descriptors only, being agnostic to the place recognition model. The experimental evaluation, conducted on the KITTI Odometry dataset, where we compared TReR with s.o.t.a. re-ranking approaches such as alphaQE and SGV, indicate the robustness and efficiency when compared to alphaQE while offering a good trade-off between robustness and efficiency when compared to SGV.

Abstract: 3D Convolutional Neural Networks are gaining increasing attention from researchers and practitioners and have found applications in many domains, such as surveillance systems, autonomous vehicles, human monitoring systems, and video retrieval. However, their widespread adoption is hindered by their high computational and memory requirements, especially when resource-constrained systems are targeted. This paper addresses the problem of mapping X3D, a state-of-the-art model in Human Action Recognition that achieves accuracy of 95.5\% in the UCF101 benchmark, onto any FPGA device. The proposed toolflow generates an optimised stream-based hardware system, taking into account the available resources and off-chip memory characteristics of the FPGA device. The generated designs push further the current performance-accuracy pareto front, and enable for the first time the targeting of such complex model architectures for the Human Action Recognition task.

Abstract: Prosthetic Joint Infection (PJI) is a prevalent and severe complication characterized by high diagnostic challenges. Currently, a unified diagnostic standard incorporating both computed tomography (CT) images and numerical text data for PJI remains unestablished, owing to the substantial noise in CT images and the disparity in data volume between CT images and text data. This study introduces a diagnostic method, HGT, based on deep learning and multimodal techniques. It effectively merges features from CT scan images and patients' numerical text data via a Unidirectional Selective Attention (USA) mechanism and a graph convolutional network (GCN)-based feature fusion network. We evaluated the proposed method on a custom-built multimodal PJI dataset, assessing its performance through ablation experiments and interpretability evaluations. Our method achieved an accuracy (ACC) of 91.4\% and an area under the curve (AUC) of 95.9\%, outperforming recent multimodal approaches by 2.9\% in ACC and 2.2\% in AUC, with a parameter count of only 68M. Notably, the interpretability results highlighted our model's strong focus and localization capabilities at lesion sites. This proposed method could provide clinicians with additional diagnostic tools to enhance accuracy and efficiency in clinical practice.

Abstract: There is high demand for online fashion recommender systems that incorporate the needs of the consumer's body shape. As such, we present a methodology to classify human body shape from a single image. This is achieved through the use of instance segmentation and keypoint estimation models, trained only on open-source benchmarking datasets. The system is capable of performing in noisy environments owing to to robust background subtraction. The proposed methodology does not require 3D body recreation as a result of classification based on estimated keypoints, nor requires historical information about a user to operate - calculating all required measurements at the point of use. We evaluate our methodology both qualitatively against existing body shape classifiers and quantitatively against a novel dataset of images, which we provide for use to the community. The resultant body shape classification can be utilised in a variety of downstream tasks, such as input to size and fit recommendation or virtual try-on systems.

Abstract: Fashion is one of the largest world's industries and computer vision techniques have been becoming more popular in recent years, in particular, for tasks such as object detection and apparel segmentation. Even with the rapid growth in computer vision solutions, specifically for the fashion industry, many problems are far for being resolved. Therefore, not at all times, adjusting out-of-the-box pre-trained computer vision models will provide the desired solution. In the present paper is proposed a pipeline that takes a noisy image with a person and specifically detects the regions with garments that are bottoms or tops. Our solution implements models that are capable of finding human parts in an image e.g. full-body vs half-body, or no human is found. Then, other models knowing that there's a human and its composition (e.g. not always we have a full-body) finds the bounding boxes/regions of the image that very likely correspond to a bottom or a top. For the creation of bounding boxes/regions task, a benchmark dataset was specifically prepared. The results show that the Mask RCNN solution is robust, and generalized enough to be used and scalable in unseen apparel/fashion data.

Abstract: Recent works have explored text-guided image editing using diffusion models and generated edited images based on text prompts. However, the models struggle to accurately locate the regions to be edited and faithfully perform precise edits. In this work, we propose a framework termed InstructEdit that can do fine-grained editing based on user instructions. Our proposed framework has three components: language processor, segmenter, and image editor. The first component, the language processor, processes the user instruction using a large language model. The goal of this processing is to parse the user instruction and output prompts for the segmenter and captions for the image editor. We adopt ChatGPT and optionally BLIP2 for this step. The second component, the segmenter, uses the segmentation prompt provided by the language processor. We employ a state-of-the-art segmentation framework Grounded Segment Anything to automatically generate a high-quality mask based on the segmentation prompt. The third component, the image editor, uses the captions from the language processor and the masks from the segmenter to compute the edited image. We adopt Stable Diffusion and the mask-guided generation from DiffEdit for this purpose. Experiments show that our method outperforms previous editing methods in fine-grained editing applications where the input image contains a complex object or multiple objects. We improve the mask quality over DiffEdit and thus improve the quality of edited images. We also show that our framework can accept multiple forms of user instructions as input. We provide the code at https://github.com/QianWangX/InstructEdit.

Abstract: This paper proposes an anticipative transformer-based model for short-term solar irradiance forecasting. Given a sequence of sky images, our proposed vision transformer encodes features of consecutive images, feeding into a transformer decoder to predict irradiance values associated with future unseen sky images. We show that our model effectively learns to attend only to relevant features in images in order to forecast irradiance. Moreover, the proposed anticipative transformer captures long-range dependencies between sky images to achieve a forecasting skill of 21.45 % on a 15 minute ahead prediction for a newly introduced dataset of all-sky images when compared to a smart persistence model.

Abstract: During ultrasonic scanning processes, real-time lesion detection can assist radiologists in accurate cancer diagnosis. However, this essential task remains challenging and underexplored. General-purpose real-time object detection models can mistakenly report obvious false positives (FPs) when applied to ultrasound videos, potentially misleading junior radiologists. One key issue is their failure to utilize negative symptoms in previous frames, denoted as negative temporal contexts (NTC). To address this issue, we propose to extract contexts from previous frames, including NTC, with the guidance of inverse optical flow. By aggregating extracted contexts, we endow the model with the ability to suppress FPs by leveraging NTC. We call the resulting model UltraDet. The proposed UltraDet demonstrates significant improvement over previous state-of-the-arts and achieves real-time inference speed. To facilitate future research, we will release the code, checkpoints, and high-quality labels of the CVA-BUS dataset used in our experiments.

Abstract: Recognizing elementary underlying concepts from observations (disentanglement) and generating novel combinations of these concepts (compositional generalization) are fundamental abilities for humans to support rapid knowledge learning and generalize to new tasks, with which the deep learning models struggle. Towards human-like intelligence, various works on disentangled representation learning have been proposed, and recently some studies on compositional generalization have been presented. However, few works study the relationship between disentanglement and compositional generalization, and the observed results are inconsistent. In this paper, we study several typical disentangled representation learning works in terms of both disentanglement and compositional generalization abilities, and we provide an important insight: vector-based representation (using a vector instead of a scalar to represent a concept) is the key to empower both good disentanglement and strong compositional generalization. This insight also resonates the neuroscience research that the brain encodes information in neuron population activity rather than individual neurons. Motivated by this observation, we further propose a method to reform the scalar-based disentanglement works ($\beta$-TCVAE and FactorVAE) to be vector-based to increase both capabilities. We investigate the impact of the dimensions of vector-based representation and one important question: whether better disentanglement indicates higher compositional generalization. In summary, our study demonstrates that it is possible to achieve both good concept recognition and novel concept composition, contributing an important step towards human-like intelligence.

Abstract: This research evaluates a convolutional neural network (CNN) based approach to forensic video steganalysis. A video steganography dataset is created to train a CNN to conduct forensic steganalysis in the spatial domain. We use a noise residual convolutional neural network to detect embedded secrets since a steganographic embedding process will always result in the modification of pixel values in video frames. Experimental results show that the CNN-based approach can be an effective method for forensic video steganalysis and can reach a detection rate of 99.96%. Keywords: Forensic, Steganalysis, Deep Steganography, MSU StegoVideo, Convolutional Neural Networks

Abstract: Text-only Image Captioning (TIC) is an approach that aims to construct a model solely based on text that can accurately describe images. Recently, diffusion models have demonstrated remarkable capabilities in generating high-quality images that are semantically coherent with given texts. This presents an opportunity to generate synthetic training images for TIC. However, we have identified a challenge that the images generated from simple descriptions typically exhibit a single perspective with one or limited contexts, which is not aligned with the complexity of real-world scenes in the image domain. In this paper, we propose a novel framework that addresses this issue by introducing multi-context data generation. Starting with an initial text corpus, our framework employs a large language model to select multiple sentences that describe the same scene from various perspectives. These sentences are then summarized into a single sentence with multiple contexts. We generate simple images using the straightforward sentences and complex images using the summarized sentences through diffusion models. Finally, we train the model exclusively using the synthetic image-text pairs obtained from this process. Experimental results demonstrate that our proposed framework effectively tackles the central challenge we have identified, achieving the state-of-the-art performance on popular datasets such as MSCOCO, Flickr30k, and SS1M.

Abstract: The expenses involved in training state-of-the-art deep hashing retrieval models have witnessed an increase due to the adoption of more sophisticated models and large-scale datasets. Dataset Distillation (DD) or Dataset Condensation(DC) focuses on generating smaller synthetic dataset that retains the original information. Nevertheless, existing DD methods face challenges in maintaining a trade-off between accuracy and efficiency. And the state-of-the-art dataset distillation methods can not expand to all deep hashing retrieval methods. In this paper, we propose an efficient condensation framework that addresses these limitations by matching the feature-embedding between synthetic set and real set. Furthermore, we enhance the diversity of features by incorporating the strategies of early-stage augmented models and multi-formation. Extensive experiments provide compelling evidence of the remarkable superiority of our approach, both in terms of performance and efficiency, compared to state-of-the-art baseline methods.

Abstract: Deep architectures consist of tens or hundreds of convolutional layers (CLs) that terminate with a few fully connected (FC) layers and an output layer representing the possible labels of a complex classification task. According to the existing deep learning (DL) rationale, the first CL reveals localized features from the raw data, whereas the subsequent layers progressively extract higher-level features required for refined classification. This article presents an efficient three-phase procedure for quantifying the mechanism underlying successful DL. First, a deep architecture is trained to maximize the success rate (SR). Next, the weights of the first several CLs are fixed and only the concatenated new FC layer connected to the output is trained, resulting in SRs that progress with the layers. Finally, the trained FC weights are silenced, except for those emerging from a single filter, enabling the quantification of the functionality of this filter using a correlation matrix between input labels and averaged output fields, hence a well-defined set of quantifiable features is obtained. Each filter essentially selects a single output label independent of the input label, which seems to prevent high SRs; however, it counterintuitively identifies a small subset of possible output labels. This feature is an essential part of the underlying DL mechanism and is progressively sharpened with layers, resulting in enhanced signal-to-noise ratios and SRs. Quantitatively, this mechanism is exemplified by the VGG-16, VGG-6, and AVGG-16. The proposed mechanism underlying DL provides an accurate tool for identifying each filter's quality and is expected to direct additional procedures to improve the SR, computational complexity, and latency of DL.

Abstract: Neural Radiance Field (NeRF) research has attracted significant attention recently, with 3D modelling, virtual/augmented reality, and visual effects driving its application. While current NeRF implementations can produce high quality visual results, there is a conspicuous lack of reliable methods for evaluating them. Conventional image quality assessment methods and analytical metrics (e.g. PSNR, SSIM, LPIPS etc.) only provide approximate indicators of performance since they generalise the ability of the entire NeRF pipeline. Hence, in this paper, we propose a new test framework which isolates the neural rendering network from the NeRF pipeline and then performs a parametric evaluation by training and evaluating the NeRF on an explicit radiance field representation. We also introduce a configurable approach for generating representations specifically for evaluation purposes. This employs ray-casting to transform mesh models into explicit NeRF samples, as well as to "shade" these representations. Combining these two approaches, we demonstrate how different "tasks" (scenes with different visual effects or learning strategies) and types of networks (NeRFs and depth-wise implicit neural representations (INRs)) can be evaluated within this framework. Additionally, we propose a novel metric to measure task complexity of the framework which accounts for the visual parameters and the distribution of the spatial data. Our approach offers the potential to create a comparative objective evaluation framework for NeRF methods.

Abstract: Rain streaks significantly decrease the visibility of captured images and are also a stumbling block that restricts the performance of subsequent computer vision applications. The existing deep learning-based image deraining methods employ manually crafted networks and learn a straightforward projection from rainy images to clear images. In pursuit of better deraining performance, they focus on elaborating a more complicated architecture rather than exploiting the intrinsic properties of the positive and negative information. In this paper, we propose a contrastive learning-based image deraining method that investigates the correlation between rainy and clear images and leverages a contrastive prior to optimize the mutual information of the rainy and restored counterparts. Given the complex and varied real-world rain patterns, we develop a recursive mechanism. It involves multi-scale feature extraction and dynamic cross-level information recruitment modules. The former advances the portrayal of diverse rain patterns more precisely, while the latter can selectively compensate high-level features for shallow-level information. We term the proposed recursive dynamic multi-scale network with a contrastive prior, RDMC. Extensive experiments on synthetic benchmarks and real-world images demonstrate that the proposed RDMC delivers strong performance on the depiction of rain streaks and outperforms the state-of-the-art methods. Moreover, a practical evaluation of object detection and semantic segmentation shows the effectiveness of the proposed method.

Abstract: Super-resolution (SR) techniques designed for real-world applications commonly encounter two primary challenges: generalization performance and restoration accuracy. We demonstrate that when methods are trained using complex, large-range degradations to enhance generalization, a decline in accuracy is inevitable. However, since the degradation in a certain real-world applications typically exhibits a limited variation range, it becomes feasible to strike a trade-off between generalization performance and testing accuracy within this scope. In this work, we introduce a novel approach to craft training degradation distributions using a small set of reference images. Our strategy is founded upon the binned representation of the degradation space and the Fr\'echet distance between degradation distributions. Our results indicate that the proposed technique significantly improves the performance of test images while preserving generalization capabilities in real-world applications.

Abstract: Unsupervised pre-training methods utilizing large and diverse datasets have achieved tremendous success across a range of domains. Recent work has investigated such unsupervised pre-training methods for model-based reinforcement learning (MBRL) but is limited to domain-specific or simulated data. In this paper, we study the problem of pre-training world models with abundant in-the-wild videos for efficient learning of downstream visual control tasks. However, in-the-wild videos are complicated with various contextual factors, such as intricate backgrounds and textured appearance, which precludes a world model from extracting shared world knowledge to generalize better. To tackle this issue, we introduce Contextualized World Models (ContextWM) that explicitly model both the context and dynamics to overcome the complexity and diversity of in-the-wild videos and facilitate knowledge transfer between distinct scenes. Specifically, a contextualized extension of the latent dynamics model is elaborately realized by incorporating a context encoder to retain contextual information and empower the image decoder, which allows the latent dynamics model to concentrate on essential temporal variations. Our experiments show that in-the-wild video pre-training equipped with ContextWM can significantly improve the sample-efficiency of MBRL in various domains, including robotic manipulation, locomotion, and autonomous driving.

Abstract: Language-based fashion image editing allows users to try out variations of desired garments through provided text prompts. Inspired by research on manipulating latent representations in StyleCLIP and HairCLIP, we focus on these latent spaces for editing fashion items of full-body human datasets. Currently, there is a gap in handling fashion image editing due to the complexity of garment shapes and textures and the diversity of human poses. In this paper, we propose an editing optimizer scheme method called Text-Driven Garment Editing Mapper (TD-GEM), aiming to edit fashion items in a disentangled way. To this end, we initially obtain a latent representation of an image through generative adversarial network inversions such as Encoder for Editing (e4e) or Pivotal Tuning Inversion (PTI) for more accurate results. An optimization-based Contrasive Language-Image Pre-training (CLIP) is then utilized to guide the latent representation of a fashion image in the direction of a target attribute expressed in terms of a text prompt. Our TD-GEM manipulates the image accurately according to the target attribute, while other parts of the image are kept untouched. In the experiments, we evaluate TD-GEM on two different attributes (i.e., "color" and "sleeve length"), which effectively generates realistic images compared to the recent manipulation schemes.

Abstract: Vision and text have been fully explored in contemporary video-text foundational models, while other modalities such as audio and subtitles in videos have not received sufficient attention. In this paper, we resort to establish connections between multi-modality video tracks, including Vision, Audio, and Subtitle, and Text by exploring an automatically generated large-scale omni-modality video caption dataset called VAST-27M. Specifically, we first collect 27 million open-domain video clips and separately train a vision and an audio captioner to generate vision and audio captions. Then, we employ an off-the-shelf Large Language Model (LLM) to integrate the generated captions, together with subtitles and instructional prompts into omni-modality captions. Based on the proposed VAST-27M dataset, we train an omni-modality video-text foundational model named VAST, which can perceive and process vision, audio, and subtitle modalities from video, and better support various tasks including vision-text, audio-text, and multi-modal video-text tasks (retrieval, captioning and QA). Extensive experiments have been conducted to demonstrate the effectiveness of our proposed VAST-27M corpus and VAST foundation model. VAST achieves 22 new state-of-the-art results on various cross-modality benchmarks. Code, model and dataset will be released at https://github.com/TXH-mercury/VAST.

Abstract: High dynamic range (HDR) imaging aims to retrieve information from multiple low-dynamic range inputs to generate realistic output. The essence is to leverage the contextual information, including both dynamic and static semantics, for better image generation. Existing methods often focus on the spatial misalignment across input frames caused by the foreground and/or camera motion. However, there is no research on jointly leveraging the dynamic and static context in a simultaneous manner. To delve into this problem, we propose a novel alignment-free network with a Semantics Consistent Transformer (SCTNet) with both spatial and channel attention modules in the network. The spatial attention aims to deal with the intra-image correlation to model the dynamic motion, while the channel attention enables the inter-image intertwining to enhance the semantic consistency across frames. Aside from this, we introduce a novel realistic HDR dataset with more variations in foreground objects, environmental factors, and larger motions. Extensive comparisons on both conventional datasets and ours validate the effectiveness of our method, achieving the best trade-off on the performance and the computational cost.

Abstract: Recent advances in robust semi-supervised learning (SSL) typically filter out-of-distribution (OOD) information at the sample level. We argue that an overlooked problem of robust SSL is its corrupted information on semantic level, practically limiting the development of the field. In this paper, we take an initial step to explore and propose a unified framework termed OOD Semantic Pruning (OSP), which aims at pruning OOD semantics out from in-distribution (ID) features. Specifically, (i) we propose an aliasing OOD matching module to pair each ID sample with an OOD sample with semantic overlap. (ii) We design a soft orthogonality regularization, which first transforms each ID feature by suppressing its semantic component that is collinear with paired OOD sample. It then forces the predictions before and after soft orthogonality decomposition to be consistent. Being practically simple, our method shows a strong performance in OOD detection and ID classification on challenging benchmarks. In particular, OSP surpasses the previous state-of-the-art by 13.7% on accuracy for ID classification and 5.9% on AUROC for OOD detection on TinyImageNet dataset. The source codes are publicly available at https://github.com/rain305f/OSP.

Abstract: Reconstructing neural radiance fields with explicit volumetric representations, demonstrated by Plenoxels, has shown remarkable advantages on training and rendering efficiency, while grid-based representations typically induce considerable overhead for storage and transmission. In this work, we present a simple and effective framework for pursuing compact radiance fields from the perspective of compression methodology. By exploiting intrinsic properties exhibiting in grid models, a non-uniform compression stem is developed to significantly reduce model complexity and a novel parameterized module, named Neural Codebook, is introduced for better encoding high-frequency details specific to per-scene models via a fast optimization. Our approach can achieve over 40 $\times$ reduction on grid model storage with competitive rendering quality. In addition, the method can achieve real-time rendering speed with 180 fps, realizing significant advantage on storage cost compared to real-time rendering methods.

Abstract: Image-Text Matching (ITM) task, a fundamental vision-language (VL) task, suffers from the inherent ambiguity arising from multiplicity and imperfect annotations. Deterministic functions are not sufficiently powerful to capture ambiguity, prompting the exploration of probabilistic embeddings to tackle the challenge. However, the existing probabilistic ITM approach encounters two key shortcomings; the burden of heavy computations due to the Monte Carlo approximation, and the loss saturation issue in the face of abundant false negatives. To overcome the issues, this paper presents an improved Probabilistic Cross-Modal Embeddings (named PCME++) by introducing a new probabilistic distance with a closed-form solution. In addition, two optimization techniques are proposed to enhance PCME++ further; first, the incorporation of pseudo-positives to prevent the loss saturation problem under massive false negatives; second, mixed sample data augmentation for probabilistic matching. Experimental results on MS-COCO Caption and two extended benchmarks, CxC and ECCV Caption, demonstrate the effectiveness of PCME++ compared to state-of-the-art ITM methods. The robustness of PCME++ is also evaluated under noisy image-text correspondences. In addition, the potential applicability of PCME++ in automatic prompt tuning for zero-shot classification is shown. The code is available at https://naver-ai.github.io/pcmepp/.

Abstract: Current approaches of Reinforcement Learning (RL) applied in urban Autonomous Driving (AD) focus on decoupling the perception training from the driving policy training. The main reason is to avoid training a convolution encoder alongside a policy network, which is known to have issues related to sample efficiency, degenerated feature representations, and catastrophic self-overfitting. However, this paradigm can lead to representations of the environment that are not aligned with the downstream task, which may result in suboptimal performances. To address this limitation, this paper proposes RLAD, the first Reinforcement Learning from Pixels (RLfP) method applied in the urban AD domain. We propose several techniques to enhance the performance of an RLfP algorithm in this domain, including: i) an image encoder that leverages both image augmentations and Adaptive Local Signal Mixing (A-LIX) layers; ii) WayConv1D, which is a waypoint encoder that harnesses the 2D geometrical information of the waypoints using 1D convolutions; and iii) an auxiliary loss to increase the significance of the traffic lights in the latent representation of the environment. Experimental results show that RLAD significantly outperforms all state-of-the-art RLfP methods on the NoCrash benchmark. We also present an infraction analysis on the NoCrash-regular benchmark, which indicates that RLAD performs better than all other methods in terms of both collision rate and red light infractions.

Abstract: A creative idea is often born from transforming, combining, and modifying ideas from existing visual examples capturing various concepts. However, one cannot simply copy the concept as a whole, and inspiration is achieved by examining certain aspects of the concept. Hence, it is often necessary to separate a concept into different aspects to provide new perspectives. In this paper, we propose a method to decompose a visual concept, represented as a set of images, into different visual aspects encoded in a hierarchical tree structure. We utilize large vision-language models and their rich latent space for concept decomposition and generation. Each node in the tree represents a sub-concept using a learned vector embedding injected into the latent space of a pretrained text-to-image model. We use a set of regularizations to guide the optimization of the embedding vectors encoded in the nodes to follow the hierarchical structure of the tree. Our method allows to explore and discover new concepts derived from the original one. The tree provides the possibility of endless visual sampling at each node, allowing the user to explore the hidden sub-concepts of the object of interest. The learned aspects in each node can be combined within and across trees to create new visual ideas, and can be used in natural language sentences to apply such aspects to new designs.

Abstract: Face Morphing Attacks pose a threat to the security of identity documents, especially with respect to a subsequent access control process, because it enables both individuals involved to exploit the same document. In this study, face embeddings serve two purposes: pre-selecting images for large-scale Morphing Attack generation and detecting potential Morphing Attacks. We build upon previous embedding studies in both use cases using the MagFace model. For the first objective, we employ an pre-selection algorithm that pairs individuals based on face embedding similarity. We quantify the attack potential of differently morphed face images to compare the usability of pre-selection in automatically generating numerous successful Morphing Attacks. Regarding the second objective, we compare embeddings from two state-of-the-art face recognition systems in terms of their ability to detect Morphing Attacks. Our findings demonstrate that ArcFace and MagFace provide valuable face embeddings for image pre-selection. Both open-source and COTS face recognition systems are susceptible to generated attacks, particularly when pre-selection is based on embeddings rather than random pairing which was only constrained by soft biometrics. More accurate face recognition systems exhibit greater vulnerability to attacks, with COTS systems being the most susceptible. Additionally, MagFace embeddings serve as a robust alternative for detecting morphed face images compared to the previously used ArcFace embeddings. The results endorse the advantages of face embeddings in more effective image pre-selection for face morphing and accurate detection of morphed face images. This is supported by extensive analysis of various designed attacks. The MagFace model proves to be a powerful alternative to the commonly used ArcFace model for both objectives, pre-selection and attack detection.

Abstract: The application of eye-tracking techniques in medical image analysis has become increasingly popular in recent years. It collects the visual search patterns of the domain experts, containing much important information about health and disease. Therefore, how to efficiently integrate radiologists' gaze patterns into the diagnostic analysis turns into a critical question. Existing works usually transform gaze information into visual attention maps (VAMs) to supervise the learning process. However, this time-consuming procedure makes it difficult to develop end-to-end algorithms. In this work, we propose a novel gaze-guided graph neural network (GNN), GazeGNN, to perform disease classification from medical scans. In GazeGNN, we create a unified representation graph that models both the image and gaze pattern information. Hence, the eye-gaze information is directly utilized without being converted into VAMs. With this benefit, we develop a real-time, real-world, end-to-end disease classification algorithm for the first time and avoid the noise and time consumption introduced during the VAM preparation. To our best knowledge, GazeGNN is the first work that adopts GNN to integrate image and eye-gaze data. Our experiments on the public chest X-ray dataset show that our proposed method exhibits the best classification performance compared to existing methods.

Abstract: Accurate Story visualization requires several necessary elements, such as identity consistency across frames, the alignment between plain text and visual content, and a reasonable layout of objects in images. Most previous works endeavor to meet these requirements by fitting a text-to-image (T2I) model on a set of videos in the same style and with the same characters, e.g., the FlintstonesSV dataset. However, the learned T2I models typically struggle to adapt to new characters, scenes, and styles, and often lack the flexibility to revise the layout of the synthesized images. This paper proposes a system for generic interactive story visualization, capable of handling multiple novel characters and supporting the editing of layout and local structure. It is developed by leveraging the prior knowledge of large language and T2I models, trained on massive corpora. The system comprises four interconnected components: story-to-prompt generation (S2P), text-to-layout generation (T2L), controllable text-to-image generation (C-T2I), and image-to-video animation (I2V). First, the S2P module converts concise story information into detailed prompts required for subsequent stages. Next, T2L generates diverse and reasonable layouts based on the prompts, offering users the ability to adjust and refine the layout to their preference. The core component, C-T2I, enables the creation of images guided by layouts, sketches, and actor-specific identifiers to maintain consistency and detail across visualizations. Finally, I2V enriches the visualization process by animating the generated images. Extensive experiments and a user study are conducted to validate the effectiveness and flexibility of interactive editing of the proposed system.

Abstract: Recently, there has been a growing interest in developing diffusion-based text-to-image generative models capable of generating coherent and well-formed visual text. In this paper, we propose a novel and efficient approach called GlyphControl to address this task. Unlike existing methods that rely on character-aware text encoders like ByT5 and require retraining of text-to-image models, our approach leverages additional glyph conditional information to enhance the performance of the off-the-shelf Stable-Diffusion model in generating accurate visual text. By incorporating glyph instructions, users can customize the content, location, and size of the generated text according to their specific requirements. To facilitate further research in visual text generation, we construct a training benchmark dataset called LAION-Glyph. We evaluate the effectiveness of our approach by measuring OCR-based metrics and CLIP scores of the generated visual text. Our empirical evaluations demonstrate that GlyphControl outperforms the recent DeepFloyd IF approach in terms of OCR accuracy and CLIP scores, highlighting the efficacy of our method.

Abstract: Collecting real-world data is often considered the bottleneck of Artificial Intelligence, stalling the research progress in several fields, one of which is camera localization. End-to-end camera localization methods are still outperformed by traditional methods, and we argue that the inconsistencies associated with the data collection techniques are restraining the potential of end-to-end methods. Inspired by the recent data-centric paradigm, we propose a framework that synthesizes large localization datasets based on realistic 3D reconstructions of the real world. Our framework, termed Synfeal: Synthetic from Real, is an open-source, data-driven simulator that synthesizes RGB images by moving a virtual camera through a realistic 3D textured mesh, while collecting the corresponding ground-truth camera poses. The results validate that the training of camera localization algorithms on datasets generated by Synfeal leads to better results when compared to datasets generated by state-of-the-art methods. Using Synfeal, we conducted the first analysis of the relationship between the size of the dataset and the performance of camera localization algorithms. Results show that the performance significantly increases with the dataset size. Our results also suggest that when a large localization dataset with high quality is available, training from scratch leads to better performances. Synfeal is publicly available at https://github.com/DanielCoelho112/synfeal.

Abstract: Leveraging large-scale image-text datasets and advancements in diffusion models, text-driven generative models have made remarkable strides in the field of image generation and editing. This study explores the potential of extending the text-driven ability to the generation and editing of multi-text conditioned long videos. Current methodologies for video generation and editing, while innovative, are often confined to extremely short videos (typically less than 24 frames) and are limited to a single text condition. These constraints significantly limit their applications given that real-world videos usually consist of multiple segments, each bearing different semantic information. To address this challenge, we introduce a novel paradigm dubbed as Gen-L-Video, capable of extending off-the-shelf short video diffusion models for generating and editing videos comprising hundreds of frames with diverse semantic segments without introducing additional training, all while preserving content consistency. We have implemented three mainstream text-driven video generation and editing methodologies and extended them to accommodate longer videos imbued with a variety of semantic segments with our proposed paradigm. Our experimental outcomes reveal that our approach significantly broadens the generative and editing capabilities of video diffusion models, offering new possibilities for future research and applications. The code is available at https://github.com/G-U-N/Gen-L-Video.

Abstract: We present Pix2Repair, an automated shape repair approach that generates restoration shapes from images to repair fractured objects. Prior repair approaches require a high-resolution watertight 3D mesh of the fractured object as input. Input 3D meshes must be obtained using expensive 3D scanners, and scanned meshes require manual cleanup, limiting accessibility and scalability. Pix2Repair takes an image of the fractured object as input and automatically generates a 3D printable restoration shape. We contribute a novel shape function that deconstructs a latent code representing the fractured object into a complete shape and a break surface. We show restorations for synthetic fractures from the Geometric Breaks and Breaking Bad datasets, and cultural heritage objects from the QP dataset, and for real fractures from the Fantastic Breaks dataset. We overcome challenges in restoring axially symmetric objects by predicting view-centered restorations. Our approach outperforms shape completion approaches adapted for shape repair in terms of chamfer distance, earth mover's distance, normal consistency, and percent restorations generated.

Abstract: We present MindEye, a novel fMRI-to-image approach to retrieve and reconstruct viewed images from brain activity. Our model comprises two parallel submodules that are specialized for retrieval (using contrastive learning) and reconstruction (using a diffusion prior). MindEye can map fMRI brain activity to any high dimensional multimodal latent space, like CLIP image space, enabling image reconstruction using generative models that accept embeddings from this latent space. We comprehensively compare our approach with other existing methods, using both qualitative side-by-side comparisons and quantitative evaluations, and show that MindEye achieves state-of-the-art performance in both reconstruction and retrieval tasks. In particular, MindEye can retrieve the exact original image even among highly similar candidates indicating that its brain embeddings retain fine-grained image-specific information. This allows us to accurately retrieve images even from large-scale databases like LAION-5B. We demonstrate through ablations that MindEye's performance improvements over previous methods result from specialized submodules for retrieval and reconstruction, improved training techniques, and training models with orders of magnitude more parameters. Furthermore, we show that MindEye can better preserve low-level image features in the reconstructions by using img2img, with outputs from a separate autoencoder. All code is available on GitHub.

Abstract: Teeth localization, segmentation, and labeling from intra-oral 3D scans are essential tasks in modern dentistry to enhance dental diagnostics, treatment planning, and population-based studies on oral health. However, developing automated algorithms for teeth analysis presents significant challenges due to variations in dental anatomy, imaging protocols, and limited availability of publicly accessible data. To address these challenges, the 3DTeethSeg'22 challenge was organized in conjunction with the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) in 2022, with a call for algorithms tackling teeth localization, segmentation, and labeling from intraoral 3D scans. A dataset comprising a total of 1800 scans from 900 patients was prepared, and each tooth was individually annotated by a human-machine hybrid algorithm. A total of 6 algorithms were evaluated on this dataset. In this study, we present the evaluation results of the 3DTeethSeg'22 challenge. The 3DTeethSeg'22 challenge code can be accessed at: https://github.com/abenhamadou/3DTeethSeg22_challenge

Abstract: Recent Multimodal Large Language Models (MLLMs) are remarkable in vision-language tasks, such as image captioning and question answering, but lack the essential perception ability, i.e., object detection. In this work, we address this limitation by introducing a novel research problem of contextual object detection -- understanding visible objects within different human-AI interactive contexts. Three representative scenarios are investigated, including the language cloze test, visual captioning, and question answering. Moreover, we present ContextDET, a unified multimodal model that is capable of end-to-end differentiable modeling of visual-language contexts, so as to locate, identify, and associate visual objects with language inputs for human-AI interaction. Our ContextDET involves three key submodels: (i) a visual encoder for extracting visual representations, (ii) a pre-trained LLM for multimodal context decoding, and (iii) a visual decoder for predicting bounding boxes given contextual object words. The new generate-then-detect framework enables us to detect object words within human vocabulary. Extensive experiments show the advantages of ContextDET on our proposed CODE benchmark, open-vocabulary detection, and referring image segmentation. Github: https://github.com/yuhangzang/ContextDET.

Abstract: In an era where images and visual content dominate our digital landscape, the ability to manipulate and personalize these images has become a necessity. Envision seamlessly substituting a tabby cat lounging on a sunlit window sill in a photograph with your own playful puppy, all while preserving the original charm and composition of the image. We present Photoswap, a novel approach that enables this immersive image editing experience through personalized subject swapping in existing images. Photoswap first learns the visual concept of the subject from reference images and then swaps it into the target image using pre-trained diffusion models in a training-free manner. We establish that a well-conceptualized visual subject can be seamlessly transferred to any image with appropriate self-attention and cross-attention manipulation, maintaining the pose of the swapped subject and the overall coherence of the image. Comprehensive experiments underscore the efficacy and controllability of Photoswap in personalized subject swapping. Furthermore, Photoswap significantly outperforms baseline methods in human ratings across subject swapping, background preservation, and overall quality, revealing its vast application potential, from entertainment to professional editing.

Abstract: Recently, large-scale pre-trained Vision and Language (VL) models have set a new state-of-the-art (SOTA) in zero-shot visual classification enabling open-vocabulary recognition of potentially unlimited set of categories defined as simple language prompts. However, despite these great advances, the performance of these zeroshot classifiers still falls short of the results of dedicated (closed category set) classifiers trained with supervised fine tuning. In this paper we show, for the first time, how to reduce this gap without any labels and without any paired VL data, using an unlabeled image collection and a set of texts auto-generated using a Large Language Model (LLM) describing the categories of interest and effectively substituting labeled visual instances of those categories. Using our label-free approach, we are able to attain significant performance improvements over the zero-shot performance of the base VL model and other contemporary methods and baselines on a wide variety of datasets, demonstrating absolute improvement of up to 11.7% (3.8% on average) in the label-free setting. Moreover, despite our approach being label-free, we observe 1.3% average gains over leading few-shot prompting baselines that do use 5-shot supervision.

Abstract: Public large-scale text-to-image diffusion models, such as Stable Diffusion, have gained significant attention from the community. These models can be easily customized for new concepts using low-rank adaptations (LoRAs). However, the utilization of multiple concept LoRAs to jointly support multiple customized concepts presents a challenge. We refer to this scenario as decentralized multi-concept customization, which involves single-client concept tuning and center-node concept fusion. In this paper, we propose a new framework called Mix-of-Show that addresses the challenges of decentralized multi-concept customization, including concept conflicts resulting from existing single-client LoRA tuning and identity loss during model fusion. Mix-of-Show adopts an embedding-decomposed LoRA (ED-LoRA) for single-client tuning and gradient fusion for the center node to preserve the in-domain essence of single concepts and support theoretically limitless concept fusion. Additionally, we introduce regionally controllable sampling, which extends spatially controllable sampling (e.g., ControlNet and T2I-Adaptor) to address attribute binding and missing object problems in multi-concept sampling. Extensive experiments demonstrate that Mix-of-Show is capable of composing multiple customized concepts with high fidelity, including characters, objects, and scenes.

Abstract: Text-to-image generation has recently witnessed remarkable achievements. We introduce a text-conditional image diffusion model, termed RAPHAEL, to generate highly artistic images, which accurately portray the text prompts, encompassing multiple nouns, adjectives, and verbs. This is achieved by stacking tens of mixture-of-experts (MoEs) layers, i.e., space-MoE and time-MoE layers, enabling billions of diffusion paths (routes) from the network input to the output. Each path intuitively functions as a "painter" for depicting a particular textual concept onto a specified image region at a diffusion timestep. Comprehensive experiments reveal that RAPHAEL outperforms recent cutting-edge models, such as Stable Diffusion, ERNIE-ViLG 2.0, DeepFloyd, and DALL-E 2, in terms of both image quality and aesthetic appeal. Firstly, RAPHAEL exhibits superior performance in switching images across diverse styles, such as Japanese comics, realism, cyberpunk, and ink illustration. Secondly, a single model with three billion parameters, trained on 1,000 A100 GPUs for two months, achieves a state-of-the-art zero-shot FID score of 6.61 on the COCO dataset. Furthermore, RAPHAEL significantly surpasses its counterparts in human evaluation on the ViLG-300 benchmark. We believe that RAPHAEL holds the potential to propel the frontiers of image generation research in both academia and industry, paving the way for future breakthroughs in this rapidly evolving field. More details can be found on a project webpage: https://raphael-painter.github.io/.

Abstract: This paper analyzes the robustness of recent 3D shape descriptors to SO(3) rotations, something that is fundamental to shape modeling. Specifically, we formulate the task of rotated 3D object instance detection. To do so, we consider a database of 3D indoor scenes, where objects occur in different orientations. We benchmark different methods for feature extraction and classification in the context of this task. We systematically contrast different choices in a variety of experimental settings investigating the impact on the performance of different rotation distributions, different degrees of partial observations on the object, and the different levels of difficulty of negative pairs. Our study, on a synthetic dataset of 3D scenes where objects instances occur in different orientations, reveals that deep learning-based rotation invariant methods are effective for relatively easy settings with easy-to-distinguish pairs. However, their performance decreases significantly when the difference in rotations on the input pair is large, or when the degree of observation of input objects is reduced, or the difficulty level of input pair is increased. Finally, we connect feature encodings designed for rotation-invariant methods to 3D geometry that enable them to acquire the property of rotation invariance.

Abstract: We present the training recipe and results of scaling up PaLI-X, a multilingual vision and language model, both in terms of size of the components and the breadth of its training task mixture. Our model achieves new levels of performance on a wide-range of varied and complex tasks, including multiple image-based captioning and question-answering tasks, image-based document understanding and few-shot (in-context) learning, as well as object detection, video question answering, and video captioning. PaLI-X advances the state-of-the-art on most vision-and-language benchmarks considered (25+ of them). Finally, we observe emerging capabilities, such as complex counting and multilingual object detection, tasks that are not explicitly in the training mix.

Abstract: Current text-to-image generation models often struggle to follow textual instructions, especially the ones requiring spatial reasoning. On the other hand, Large Language Models (LLMs), such as GPT-4, have shown remarkable precision in generating code snippets for sketching out text inputs graphically, e.g., via TikZ. In this work, we introduce Control-GPT to guide the diffusion-based text-to-image pipelines with programmatic sketches generated by GPT-4, enhancing their abilities for instruction following. Control-GPT works by querying GPT-4 to write TikZ code, and the generated sketches are used as references alongside the text instructions for diffusion models (e.g., ControlNet) to generate photo-realistic images. One major challenge to training our pipeline is the lack of a dataset containing aligned text, images, and sketches. We address the issue by converting instance masks in existing datasets into polygons to mimic the sketches used at test time. As a result, Control-GPT greatly boosts the controllability of image generation. It establishes a new state-of-art on the spatial arrangement and object positioning generation and enhances users' control of object positions, sizes, etc., nearly doubling the accuracy of prior models. Our work, as a first attempt, shows the potential for employing LLMs to enhance the performance in computer vision tasks.

Abstract: We present BRIGHT, a bi-levelfeature representation for an imagecollection, consisting of a per-image latent space on top of a multi-scale feature grid space. Our representation is learned by an autoencoder to encode images intocontinuouskey codes, which are used to retrieve features fromgroups of multi-resolution hashtables. Our key codes and hash tables are trained together continuously with well-defined gradient flows, leading to high usage of the hash table entries and improved generative modeling compared to discrete Vector Quantization (VQ). Differently from existing continuous representations such as KL-regularized latent codes, our key codes are strictly bounded in scale and variance. Overall, feature encoding by BRIGHT is compact, efficient to train, and enables generative modeling over the image codes using state-of-the-art generators such as latent diffusion models(LDMs). Experimental results show that our method achieves comparable recon-struction results to VQ methods while having a smaller and more efficient decoder network. By applying LDM over our key code space, we achieve state-of-the-art performance on image synthesis on the LSUN-Church and human-face datasets.