24 citations · 61 across the 17 of their papers we have counts for
17 papers
Robust Global Structure-from-Motion via View Graph Pruning
Jiamin Xu, Lixing Yao, Weichen Dai +4
Structure-from-Motion (SfM) aims to estimate camera poses and reconstruct 3D structures from a collection of unordered images. Compared with incremental SfM, global SfM achieves be…
WildShadowRemover: In-the-Wild Video Shadow Removal via Detail-Preserving Video Diffusion Models
Jiamin Xu, Cong Wang, Zheng Dong +4
Video shadow removal in the wild remains challenging due to complex illumination, diverse shadow appearances, and limited training data. Despite its importance to numerous vision a…
Robust Activation Map Rectification for Weakly Supervised Volumetric Segmentation: Temporal Coherence as a Free Lunch
Renshu Gu, Jialiang Chen, Fei Gao +8
Weakly supervised segmentation relies heavily on class activation maps (CAMs) to initially localize target regions. However, CAMs are often noisy and prone to catastrophic failures…
SLAP: Stratified Loss-based Pruning for On-Policy Data-Efficient Instruction Tuning
Run Zou, Jianhang Ding, Yifan Ding +3
Instruction tuning has optimized the specialized capabilities of large language models (LLMs), but it often requires extensive datasets and prolonged training times. The challenge…
Detail-Preserving Latent Diffusion for Stable Shadow Removal
Jiamin Xu, Yuxin Zheng, Zelong Li +4
Achieving high-quality shadow removal with strong generalizability is challenging in scenes with complex global illumination. Due to the limited diversity in shadow removal dataset…
Robust and Feature-Preserving Offset Meshing
Hongyi Cao, Gang Xu, Renshu Gu +5
We introduce a novel offset meshing approach that can robustly handle a 3D surface mesh with an arbitrary geometry and topology configurations, while nicely capturing the sharp fea…
OmniSR: Shadow Removal under Direct and Indirect Lighting
Jiamin Xu, Zelong Li, Yuxin Zheng +4
Shadows can originate from occlusions in both direct and indirect illumination. Although most current shadow removal research focuses on shadows caused by direct illumination, shad…
Class-balanced Open-set Semi-supervised Object Detection for Medical Images
Zhanyun Lu, Renshu Gu, Huimin Cheng +8
Medical image datasets in the real world are often unlabeled and imbalanced, and Semi-Supervised Object Detection (SSOD) can utilize unlabeled data to improve an object detector. H…
TTMFN: Two-stream Transformer-based Multimodal Fusion Network for Survival Prediction
Ruiquan Ge, Xiangyang Hu, Rungen Huang +8
Survival prediction plays a crucial role in assisting clinicians with the development of cancer treatment protocols. Recent evidence shows that multimodal data can help in the diag…
A Parallel Feature-preserving Mesh Variable Offsetting Method with Dynamic Programming
Hongyi Cao, Gang Xu, Renshu Gu +3
Mesh offsetting plays an important role in discrete geometric processing. In this paper, we propose a parallel feature-preserving mesh offsetting framework with variable distance.…
VTP: Volumetric Transformer for Multi-view Multi-person 3D Pose Estimation
Yuxing Chen, Renshu Gu, Ouhan Huang +1
This paper presents Volumetric Transformer Pose estimator (VTP), the first 3D volumetric transformer framework for multi-view multi-person 3D human pose estimation. VTP aggregates…
Resistance-Time Co-Modulated PointNet for Temporal Super-Resolution Simulation of Blood Vessel Flows
Zhizheng Jiang, Fei Gao, Renshu Gu +3
In this paper, a novel deep learning framework is proposed for temporal super-resolution simulation of blood vessel flows, in which a high-temporal-resolution time-varying blood ve…
Track without Appearance: Learn Box and Tracklet Embedding with Local and Global Motion Patterns for Vehicle Tracking
Gaoang Wang, Renshu Gu, Zuozhu Liu +3
Vehicle tracking is an essential task in the multi-object tracking (MOT) field. A distinct characteristic in vehicle tracking is that the trajectories of vehicles are fairly smooth…
LASOR: Learning Accurate 3D Human Pose and Shape Via Synthetic Occlusion-Aware Data and Neural Mesh Rendering
Kaibing Yang, Renshu Gu, Maoyu Wang +2
A key challenge in the task of human pose and shape estimation is occlusion, including self-occlusions, object-human occlusions, and inter-person occlusions. The lack of diverse an…
Split and Connect: A Universal Tracklet Booster for Multi-Object Tracking
Gaoang Wang, Yizhou Wang, Renshu Gu +2
Multi-object tracking (MOT) is an essential task in the computer vision field. With the fast development of deep learning technology in recent years, MOT has achieved great improve…
Exploring Severe Occlusion: Multi-Person 3D Pose Estimation with Gated Convolution
Renshu Gu, Gaoang Wang, Jenq-Neng Hwang
3D human pose estimation (HPE) is crucial in many fields, such as human behavior analysis, augmented reality/virtual reality (AR/VR) applications, and self-driving industry. Videos…
Exploit the Connectivity: Multi-Object Tracking with TrackletNet
Gaoang Wang, Yizhou Wang, Haotian Zhang +2
Multi-object tracking (MOT) is an important and practical task related to both surveillance systems and moving camera applications, such as autonomous driving and robotic vision. H…