48 accepted papers
Confidence estimation for stereo matching is crucial for enhancing the reliability and accuracy of depth perception in real-world applications. Despite effectively capturing aleatoric uncertainty through probabilistic modeling and statistical aggregation, current regression-based confidence estimati…
Curvilinear structure segmentation is essential in domains such as medical imaging, remote sensing, and materials science. Existing methods often require extensive domain-specific training and lack generalization to novel domains. To overcome these limitations, we propose the Segment Anything Curve
Knowledge distillation (KD) transfers the ``dark knowledge
Establishing reliable image correspondences is essential for many robotic vision problems. However, existing methods often struggle in challenging scenarios with large viewpoint changes or textureless regions, where incorrect correspondences may still receive high similarity scores. This is mainly b…
Dynamically Reconfigurable Battery (DRB) systems employ power electronic switches to create dynamic topologies. They enable effective management of cell difference through real-time adjustment of cell connections. However, existing DRB control methods struggle to learn effective strategies due to sp
Neural Radiance Fields (NeRF) have shown remarkable success in image novel view synthesis (NVS), inspiring extensions to LiDAR NVS. However, most methods heavily rely on accurate camera poses for scene reconstruction. The sparsity and textureless nature of LiDAR data also present distinct challenges
Knowledge distillation transfers "dark knowledge" from a large teacher model to a smaller student model, yielding a highly efficient network. To improve network's generalization ability, existing works use a larger temperature coefficient for knowledge distillation. Nevertheless, these methods may…
In clinical practice of echocardiography examinations, multiple planes containing the heart structures of different view are usually required in screening, diagnosis and treatment of cardiac disease. AI models for echocardiography have to be tailored for a specific plane due to the dramatic structur…
Dense feature matching methods aim to estimate a dense correspondence field between images. Inaccurate correspondence can occur due to the presence of unmatchable region, necessitating the need for certainty measurement. This is typically addressed by training a binary classifier to decide whether e…
Massive human-related data is collected to train neural networks for computer vision tasks. A major conflict is exposed relating to software engineers between better developing AI systems and distancing from the sensitive training data. To reconcile this conflict, the paper proposes an efficient pri
Robust and efficient local feature matching plays a crucial role in applications such as SLAM and visual localization for robotics. Despite great progress, it is still very challenging to extract robust and discriminative visual features in scenarios with drastic lighting changes, low texture areas,
Category-level 6D pose estimation in cluttered and occluded environments is a challenging task. Most existing methods rely on deterministic point-based correspondences to estimate target poses, which cannot consider the uncertainty for occluded objects, and thus result in inferior performance. In th
Online stereo rectification is critical for autonomous vehicles and robots in dynamic environments, where factors such as vibration, temperature fluctuations, and mechanical stress can affect rectification accuracy and severely degrade downstream stereo depth estimation. Current dominant approaches…
In the domain of Simultaneous Localization and Mapping (SLAM), loop closure is a linchpin for achieving accurate and consistent 3D environment mapping. However, the process is fraught with abrupt light changes and motion blur. These elements introduce uncertainties and inaccuracies in the data captu
Prompt learning has attracted widespread attention in adapting vision-language models to downstream tasks. Existing methods largely rely on optimization strategies to ensure the task-awareness of learnable prompts. Due to the scarcity of task-specific data, overfitting is prone to occur. The resulti…
The soft-argmax operation is widely adopted in neural network-based stereo matching methods to enable differentiable regression of disparity. However, networks trained with soft-argmax tend to predict multimodal probability distributions due to the absence of explicit constraints on the shape of the
Rotated object detection aims to locate and classify objects with arbitrary orientations. In complex backgrounds, small rotated objects with limited salient features present challenges for standard backbones to extract high-quality, discriminative features. Additionally, traditional single-stage det…
Emergent Large Language Models (LLMs) use their extraordinary performance and powerful deduction capacity to discern from traditional language models. However, the expenses of computational resources and storage for these LLMs are stunning, quantization then arises as a trending conversation. To add…
Real-world noise removal is crucial in low-level computer vision. Due to the remarkable generation capabilities of diffusion models, recent attention has shifted towards leveraging diffusion priors for image restoration tasks. However, existing diffusion priors-based methods either consider simple n…
In recent years, numerous real-time stereo matching methods have been introduced, but they often lack accuracy. These methods attempt to improve accuracy by introducing new modules or integrating traditional methods. However, the improvements are only modest. In this paper, we propose a novel strate…
Since rain shows a variety of shapes and directions, learning the degradation representation is extremely challenging for single image deraining. Existing methods mainly propose to designing complicated modules to implicitly learn latent degradation representation from rainy images. However, it is h…
Geometric knowledge has been shown to be beneficial for the stereo matching task. However prior attempts to integrate geometric insights into stereo matching algorithms have largely focused on geometric knowledge from single images while crucial cross-view factors such as occlusion and matching uniq…
"Surgical scene perception via videos is critical for advancing robotic surgery, telesurgery, and AI-assisted surgery, particularly in ophthalmology. However, the scarcity of diverse and richly annotated video datasets has hindered the development of intelligent systems for surgical workflow analysi…
Monocular depth estimation obtaining scene depth information from a single image is an important task in the field of computer vision. Constrained by the limitations of convolutional networks in conducting long-distance modeling and the underutilization of datasets, the generalization of existing mo…
Visual Place Recognition (VPR) is critical for navigation and loop closure in autonomous driving tasks, mitigating the impact of shift errors caused by dynamic changes in the environment. Due to the limited ability of backbone networks and extreme environmental changes, current methods fail to captu…
Keypoints-based approaches have shown to be promising for retinal image registration, which superimpose two or more images from different views based on keypoint detection and description. However, existing approaches suffer from ineffective keypoint detector and descriptor training. Meanwhile, the…
Image denoising is a fundamental task in computer vision. While prevailing deep learning-based supervised and self-supervised methods have excelled in eliminating in-distribution noise their susceptibility to out-of-distribution (OOD) noise remains a significant challenge. The recent emergence of co…
"A picture is worth a thousand words", significantly beyond mere a categorization. Accompanied by that, many patches of the image could have completely irrelevant meanings with the categorization if they were independently observed. This could significantly reduce the efficiency of a large family of…
Although existing stereo matching models have achieved continuous improvement, they often face issues related to trustworthiness due to the absence of uncertainty estimation. Additionally, effectively leveraging multi-scale and multi-view knowledge of stereo pairs remains unexplored. In this paper,…
Monocular self-supervised depth estimation with a low-cost sensor is the mainstream solution to gathering dense depth maps for robots and autonomous driving. In this paper, based on the philosophy "less is more" (i.e., focusing only on valid pixels in sparse LiDAR), we propose a novel framework, Eff…
Category-level 6D pose and size estimation is to estimate the rotation, translation and size of the observed instance objects from an arbitrary angle in a cluttered scene. Compared with instance-level 6D pose estimation, there are two main challenges for category-level 6D pose estimation. One is tha…
High-performance real-time 3D object detection is crucial in autonomous driving perception systems. Voxel-or point-based 3D object detectors are highly accurate but inefficient and difficult to deploy, while other methods use 2D projection views to improve efficiency, but information loss usually de…
Transformer-based text-to-image synthesis generates images from abstractive textual conditions and achieves prompt results. Since transformer-based models predict visual tokens step by step in testing, where the early error is hard to be corrected and would be propagated. To alleviate this issue, th…
Real-world single image denoising is crucial and practical in computer vision. Bayesian inversions combined with score priors now have proven effective for single image denoising but are limited to white Gaussian noise. Moreover, applying existing score-based methods for real-world denoising require…
Recently deep learning techniques have significantly advanced image super-resolution (SR). Due to the black-box nature, quantifying reconstruction uncertainty is crucial when employing these deep SR networks. Previous approaches for SR uncertainty estimation mostly focus on capturing pixel-wise unce…
Indoor 3D object detection based on point clouds has been widely applied for robotics, augmented reality and virtual reality. The point clouds generated from RGB-D cameras are sparse for distant objects, which affects the detection performance. Multimodal 3D object detection can improve the detectio
Object-guided text-to-image synthesis aims to generate images from natural language descriptions built by two-step frameworks, i.e., the model generates the layout and then synthesizes images from the layout and captions. However, such frameworks have two issues: 1) complex structure, since generati…
6D pose estimation of objects is an important part of robot grasping. The latest research trend on 6D pose estimation is to train a deep neural network to directly predict the 2D projection position of the 3D key points from the image, establish the corresponding relationship, and finally use Pespec…
Skeleton-based person re-identification (Re-ID) is an emerging open topic providing great value for safety-critical applications. Existing methods typically extract hand-crafted features or model skeleton dynamics from the trajectory of body joints, while they rarely explore valuable relation inform…
Anomaly detection in retinal image refers to the identification of abnormality caused by various retinal diseases/lesions, by only leveraging normal images in training phase. Normal images from healthy subjects often have regular structures (e.g., the structured blood vessels in the fundus image, or…
Text-to-image synthesis is a challenging task that generates realistic images from a textual sequence, which usually contains limited information compared with the corresponding image and so is ambiguous and abstractive. The limited textual information only describes a scene partly, which will compl…
Gait-based person re-identification (Re-ID) is valuable for safety-critical applications, and using only 3D skeleton data to extract discriminative gait features for person Re-ID is an emerging open topic. Existing methods either adopt hand-crafted features or learn gait features by traditional supe…
This paper presents a novel feature-based method that is built upon a convolutional neural network (CNN) to learn the deep representation for multimodal retinal image registration. We coined the algorithm deep step patterns, in short DeepSPa. Most existing deep learning based methods require a set o…
Few-shot learning aims to learn latent patterns from few training examples and has shown promises in practice. However, directly calculating the distances between the query image and support image in existing methods may cause ambiguity because dominant objects can locate anywhere on images. To addr…
Single-image super-resolution restores the lost structures and textures from low-resolved images, which has achieved extensive attention from the research community. The top performers in this field include deep or wide convolutional neural networks, or recurrent neural networks. However, the method…
The reconstruction and analysis of tree-like topological structures in the biomedical images is crucial for biologists and surgeons to understand biomedical conditions and plan surgical procedures. The underlying tree-structure topology reveals how different curvilinear components are anatomically…
Glaucoma is one of the leading cause of blindness. Although there is still no cure, early detection can prevent serious vision loss. Therefore automated glaucoma detection/classification is an important issue. In the past decade, segmentation based approach such as those based on cup-to-disc-ratio a…
Existing feature descriptor-based methods on retinal image registration are mainly based on scale-invariant feature transform (SIFT) or partial intensity invariant feature descriptor (PIIFD). While these descriptors are often being exploited, they do not work very well upon unhealthy multimodal imag…