4 citations · 4 across the 15 of their papers we have counts for
11 papers · 1 filter
SnapFlow: One-Step Action Generation for Flow-Matching VLAs via Progressive Self-Distillation
Wuyang Luan, Junhui Li, Weiguang Zhao +3
Vision-language-action (VLA) models with flow-matching action heads, such as π0 and π0.5, have become a standard recipe for generalist robot manipulation, but every action chunk is…
TrajVG: 3D Trajectory-Coupled Visual Geometry Learning
Xingyu Miao, Weiguang Zhao, Tao Lu +5
Feed-forward multi-frame 3D reconstruction models often degrade on videos with object motion. Global-reference becomes ambiguous under multiple motions, while the local pointmap re…
SynthVerse: A Large-Scale Diverse Synthetic Dataset for Point Tracking
Weiguang Zhao, Haoran Xu, Xingyu Miao +11
Point tracking aims to follow visual points through complex motion, occlusion, and viewpoint changes, and has advanced rapidly with modern foundation models. Yet progress toward ge…
Unlock Pose Diversity: Accurate and Efficient Implicit Keypoint-based Spatiotemporal Diffusion for Audio-driven Talking Portrait
Chaolong Yang, Kai Yao, Yuyao Yan +7
Audio-driven single-image talking portrait generation plays a crucial role in virtual reality, digital human creation, and filmmaking. Existing approaches are generally categorized…
BFANet: Revisiting 3D Semantic Segmentation with Boundary Feature Analysis
Weiguang Zhao, Rui Zhang, Qiufeng Wang +2
3D semantic segmentation plays a fundamental and crucial role to understand 3D scenes. While contemporary state-of-the-art techniques predominantly concentrate on elevating the ove…
HOMER: Homography-Based Efficient Multi-view 3D Object Removal
Jingcheng Ni, Weiguang Zhao, Daniel Wang +4
3D object removal is an important sub-task in 3D scene editing, with broad applications in scene understanding, augmented reality, and robotics. However, existing methods struggle…
Towards Training-Free Open-World Classification with 3D Generative Models
Xinzhe Xia, Weiguang Zhao, Yuyao Yan +4
3D open-world classification is a challenging yet essential task in dynamic and unstructured real-world scenarios, requiring both open-category and open-pose recognition. To addres…
PO3AD: Predicting Point Offsets toward Better 3D Point Cloud Anomaly Detection
Jianan Ye, Weiguang Zhao, Xi Yang +2
Point cloud anomaly detection under the anomaly-free setting poses significant challenges as it requires accurately capturing the features of 3D normal data to identify deviations…
Open-Pose 3D Zero-Shot Learning: Benchmark and Challenges
Weiguang Zhao, Guanyu Yang, Rui Zhang +5
With the explosive 3D data growth, the urgency of utilizing zero-shot learning to facilitate data labeling becomes evident. Recently, methods transferring language or language-imag…
Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarization
Weiguang Zhao, Yuyao Yan, Chaolong Yang +3
Instance segmentation on point clouds is crucially important for 3D scene understanding. Most SOTAs adopt distance clustering, which is typically effective but does not perform wel…
From 2D Images to 3D Model:Weakly Supervised Multi-View Face Reconstruction with Deep Fusion
Weiguang Zhao, Chaolong Yang, Jianan Ye +6
While weakly supervised multi-view face reconstruction (MVR) is garnering increased attention, one critical issue still remains open: how to effectively interact and fuse multiple…