40 accepted papers
Recently, deep learning–based methods for road crack segmentation have achieved promising performance, particularly in robotic vision applications such as automated inspection and maintenance. However, most frequency-domain methods employ a decoupled processing strategy, overlooking the dynamic modu…
3D semantic occupancy prediction is crucial for autonomous driving perception, offering comprehensive geometric scene understanding and semantic recognition. However, existing methods struggle with geometric misalignment in view transformation due to lack of pixel-level accurate depth estimation, an
Estimating continuous optical flow is a fundamental yet challenging problem in dynamic visual perception. Event-based cameras, with microsecond latency and high dynamic range, capture brightness changes asynchronously, offering a unique opportunity to model motion with fine temporal precision. Howev
Existing GUI grounding methods often struggle with fine-grained localization in high-resolution screenshots. To address this, we propose GUI-ARP, a novel framework that enables adaptive multi-stage inference. Equipped with the proposed Adaptive Region Perception (ARP) and Adaptive Stage Controlling…
The existing methods for novel view synthesis depend on dense input images and accurate camera poses, which significantly limits their practical application. We propose a novel framework that enables high-quality sparse-view reconstruction via 3D Gaussian Splatting (3DGS) without knowing camera pose…
Camera localization within LiDAR maps has gained significant attention due to its potential for accurate positioning with low-cost and lightweight sensors compared to LiDAR-based systems. However, existing methods often prioritize localization accuracy, sometimes compromising efficiency, which can l…
Adversarial examples pose serious threats to deep neural networks (DNNs), revealing fundamental vulnerabilities in model robustness. However, most existing adversarial attacks directly manipulate densely activated and highly redundant feature representations, which often leads to overfitting on surr…
Global localization, encompassing robust place recognition and precise transformation estimation, is crucial for mobile robot navigation when the global navigation satellite system (GNSS) is unavailable. While LiDAR-based approaches are favored for their accuracy in 3D perception and resilience to i
Real-time tracking of previously unseen, highly dynamic objects in contact-rich scenes, such as during dexterous in-hand manipulation, remains a major challenge. Pure vision-based approaches often fail under heavy occlusions due to frequent contact interactions and motion blur caused by abrupt impac…
Event cameras are bio-inspired sensors that are capable of capturing motion information with high temporal resolution, which show potential in aiding image motion deblurring recently. Most existing methods indiscriminately handle feature fusion of two modalities with symmetric unidirectional/bidirec…
In this letter, we propose ContactSDF, a method that uses signed distance functions (SDFs) to approximate multi-contact models, including both collision detection and time-stepping routines. ContactSDF first establishes an SDF using the supporting plane representation of an object for collision dete
In this paper, we propose a differential-flatness-based controller (DFBC) for precise trajectory tracking of tractor-trailers, particularly during reversing maneuvers, which are challenging due to unstable equilibrium points. The proposed controller leverages the differential flatness property of tr
Camera localization within LiDAR maps has gained significant attention due to its potential for accurate positioning with low-cost and lightweight sensors compared to LiDAR-based systems. However, existing methods often prioritize localization accuracy, sometimes compromising efficiency, which can l
Direct Preference Optimization (DPO) has become a prominent method for aligning Large Language Models (LLMs) with human preferences. While DPO has enabled significant progress in aligning English LLMs, multilingual preference alignment is hampered by data scarcity. To address this, we propose a nove…
Recent advances have demonstrated that integrating reinforcement learning with rule-based rewards can significantly enhance the reasoning capabilities of large language models (LLMs), even without supervised fine-tuning (SFT). However, prevalent reinforcement learning algorithms such as GRPO and its…
Large Language Models (LLMs) have achieved state-of-the-art performance across numerous tasks. However, these advancements have predominantly benefited "first-class" languages such as English and Chinese, leaving many other languages underrepresented. This imbalance, while limiting broader applicati…
This paper introduces LiGSM, a novel LiDARenhanced 3D Gaussian Splatting (3DGS) mapping framework that improves the accuracy and robustness of 3D scene mapping by integrating LiDAR data. LiGSM constructs joint loss from images and LiDAR point clouds to estimate the poses and optimize their extrinsic
Making multi-camera visual SLAM systems easier to set up and more robust to the environment is attractive for vision robots. Existing monocular and binocular vision SLAM systems have narrow sensing Field-of-View (FoV), resulting in degenerated accuracy and limited robustness in textureless environme
Transfer-based attacks pose a significant security threat to deep neural networks (DNNs), due to their strong performance on unseen models in real-world black-box scenarios. Building on this, feature importance-based attacks further improve the transferability of adversarial examples by effectively…
In visual question answering (VQA) context, users often pose ambiguous questions to visual language models (VLMs) due to varying expression habits. Existing research addresses such ambiguities primarily by rephrasing questions. These approaches neglect the inherently interactive nature of user inter…
"∗ Equal contribution Corresponding author (xuchangeis@whu.edu.cn) Cross-view geo-localization aims at localizing a ground-level query image by matching it to its corresponding geo-referenced aerial view. In real-world scenarios, the task requires accommodating diverse ground images captured by user…
Keypoint detection and tracking in traditional image frames are often compromised by image quality issues such as motion blur and extreme lighting conditions. Event cameras offer potential solutions to these challenges by virtue of their high temporal resolution and high dynamic range. However, they…
Camera localization in LiDAR maps has become increasingly popular due to its promising ability to handle complex scenarios, surpassing the limitations of visual-only localization methods. However, existing approaches mostly focus on addressing the cross-modal 2D–3D gaps while overlooking the relatio
Motion deblurring can be advanced by exploiting informative features from supplementary sensors such as event cameras, which can capture rich motion information asynchronously with high temporal resolution. Existing event-based motion deblurring methods neither consider the modality redundancy in sp…
Recent research has shown that an adversary can use a surrogate model to steal the functionality of a target deep learning model even under the black-box condition and without data curation, while the existing defense mainly relies on API poisoning to disturb the surrogate training. Unfortunately, d…
This paper presents a novel framework to learn a concise geometric primitive representation for 3D point clouds. Different from representing each type of primitive individually, we focus on the challenging problem of how to achieve a concise and uniform representation robustly. We employ quadrics to…
Robust keypoint detection and tracking are crucial for various robotic tasks. However, conventional cameras struggle under rapid motion and lighting changes, hindering local and edge feature extraction essential for keypoint detection and tracking. Event cameras offer advantages in such scenarios du
Large language models respond well in high-resource languages like English but struggle in low-resource languages. It may arise from the lack of high-quality instruction following data in these languages. Directly translating English samples into these languages can be a solution but unreliable, lea…
Detecting arbitrarily oriented tiny objects poses intense challenges to existing detectors, especially for label assignment. Despite the exploration of adaptive label assignment in recent oriented object detectors, the extreme geometry shape and limited feature of oriented tiny objects still induce…
Event-based motion deblurring has shown promising results by exploiting low-latency events. However, current approaches are limited in their practical usage, as they assume the same spatial resolution of inputs and specific blurriness distributions. This work addresses these limitations and aims to…
Lidar point cloud distortion from moving object is an important problem in autonomous driving, and recently becomes more demanding with the emerging of oscillating type lidars, which feature back-and-forth scanning patterns and complex distortions. Accurately correcting the point cloud distortion wo
"Detecting tiny objects is one of the main obstacles hindering the development of object detection. The performance of generic object detectors tends to drastically deteriorate on tiny object detection tasks. In this paper, we point out that either box prior in the anchor-based detector or point pri…
The Event-based Synthetic Aperture Imaging (E-SAI) has recently been proposed to see through extremely dense occlusions. However, the performance of E-SAI is not consistent under sparse occlusions due to the dramatic decrease of signal events. This paper addresses this problem by leveraging the meri…
We present a Visual-Inertial Odometry (VIO) algorithm with multiple non-overlapping monocular cameras aiming at improving the robustness of the VIO algorithm. An initialization scheme and tightly-coupled bundle adjustment for multiple non-overlapping monocular cameras are proposed. With more stable…
"There are good arguments to support the claim that deep neural networks (DNNs) capture better feature representations than the previous hand-crafted feature engineering, which leads to a significant performance improvement. In this paper, we move a tiny step towards understanding the dynamics of fe…
Synthetic aperture imaging (SAI) is able to achieve the see through effect by blurring out the off-focus foreground occlusions and reconstructing the in-focus occluded targets from multi-view images. However, very dense occlusions and extreme lighting conditions may bring significant disturbances to…
In this paper, we propose an end-to-end learning framework for event-based motion deblurring in a self-supervised manner, where real-world events are exploited to alleviate the performance degradation caused by data inconsistency. To achieve this end, optical flows are predicted from events, with wh…
Event-based cameras are a new type of vision sensor that can encode spatial-temporal context in a pixel-level event stream. Its appealing properties offer great potential for applications requiring low processing latency and low power consumption. As an effective representation of events, the surfac
With extremely high temporal resolution, event cameras have a large potential for robotics and computer vision. However, their asynchronous imaging mechanism often aggravates the measurement sensitivity to noises and brings a physical burden to increase the image spatial resolution. To recover high-…
Light-weight camera localization in existing maps is essential for vision-based navigation. Currently, visual and visual-inertial odometry (VO&VIO) techniques are well-developed for state estimation but with inevitable accumulated drifts and pose jumps upon loop closure. To overcome these problems,…