3 papers
cs.CV2026
MotionHalluc: Diagnosing Kinematic Hallucinations in Fine-Grained Motion Reasoning
Weile Guo, Shenghong He, Danying Mo +3
Motion instruction generation in cross-video comparison aims to produce corrective feedback that describes the differences between a query and a reference motion. However, existing…
cs.CV2025
DBGroup: Dual-Branch Point Grouping for Weakly Supervised 3D Semantic Instance Segmentation
Xuexun Liu, Xiaoxu Xu, Qiudan Zhang +2
Weakly supervised 3D instance segmentation is essential for 3D scene understanding, especially as the growing scale of data and high annotation costs associated with fully supervis…
cs.CV2025
3D Weakly Supervised Semantic Segmentation via Class-Aware and Geometry-Guided Pseudo-Label Refinement
Xiaoxu Xu, Xuexun Liu, Jinlong Li +5
3D weakly supervised semantic segmentation (3D WSSS) aims to achieve semantic segmentation by leveraging sparse or low-cost annotated data, significantly reducing reliance on dense…