Human demonstrations are a scalable data source for learning dexterous manipulation, but the embodiment gap prevents human motion from being executed directly on robots. Inverse kinematics (IK) retargets human motion to robots efficiently but ignores dynamics, often producing infeasible motions. Reinforcement learning...
De-Chen Gao, Yue Yang, Ben Abbatematteo et al.· 0 citations
Gaussian Splatting has emerged as a prominent technique in computer vision and graphics, enabling high-fidelity scene reconstruction from a vast collection of 3D Gaussian primitives. Each primitive's appearance is governed by a viewindependent opacity parameter and a view-dependent color derived from spherical harmonic...
Hao-Chen Sun, Rui Xu, Zhiyang Dou et al.· IEEE Transactions on Visuali...· 0 citations
Quantifying collective fish behavior requires accurate trajectories, yet multi-view 3D tracking remains challenging due to frequent occlusions, visually similar individuals, and the long-standing scarcity of identity annotations. We present TrackFish3D, a geometry-driven self-supervised framework for dense multi-camera...
P. Phurtivilai, Zhiyang Dou, Yi-Fan Wu et al.· 0 citations
Modeling human reactions to spatial audio requires understanding both what is heard and where it comes from. Prior work generates motion offline from complete acoustic and spatial input sequences. Humans, however, react to sounds without knowing what they will hear next. We present Sonic-AMG, to our knowledge the first...
Generating high-quality and controllable camera motion is essential for AI-assisted cinematography, video synthesis, and 3D scene understanding. We introduce TKCAM, a Text- and Keyframe-conditioned CAMera-motion synthesis framework based on generative masked modeling. We represent camera dynamics using a 12-dimensional...
Hao-Zhe Yang, Zhiyang Dou, Ze-Kai Gu et al.· 0 citations
Part segmentation is a fundamental problem in computer graphics and 3D vision. Recent works have expanded 3D part segmentation beyond fixed taxonomies, but existing approaches typically only address a specific setting, such as text-guided part segmentation or point-based interaction. In this work, we argue that these s...
Zhe Zhu, Yi-Heng Zhang, Peng Li et al.· 1 citation
STAM is introduced, a dataset of motion sequences paired with spatial audio and detailed textual annotations whose rich vocabulary affords precise and nuanced specification of human motions, and MoSAT, a latent flow-matching framework for full-body motion generation jointly conditioned on natural-language intent and di...
Shu-Yang Xu, Zhiyang Dou, Yiduo Hao et al.· 0 citations
This work proposes Ms.Forcing, an efficient streaming video generation paradigm that adapts spatial granularity to each state's noise level and introduces Homogeneous-Noise-Level DMD, which assembles each fake video from clean predictions sharing the same source noise level, thereby reducing the mismatch between DMD tr...
Zekun Li, Xiaoyan Cong, Hongyu Li et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
