3 papers
cs.CV2026
Real2Sim in HOI: Toward Physically Plausible HOI Reconstruction from Monocular Videos
Yubo Zhao, Yujin Chai, Yunao Dong +4
Recovering 4D human-object interaction (HOI) from monocular video is a key step toward scalable 3D content creation, embodied AI, and simulation-based learning. Recent methods can…
cs.GR2026
Animator-Centric Skeleton Generation on Objects with Fine-Grained Details
Mingze Sun, Cheng Zeng, Jiansong Pei +7
Skeleton generation is essential for animating 3D assets, but current deep learning methods remain limited: they cannot handle the growing structural complexity of modern models an…
cs.CV2025
WATCH: World-aware Allied Trajectory and pose reconstruction for Camera and Human
Qijun Ying, Zhongyuan Hu, Rui Zhang +3
Global human motion reconstruction from in-the-wild monocular videos is increasingly demanded across VR, graphics, and robotics applications, yet requires accurate mapping of human…