8 papers
Controllable Text-to-Motion Generation via Modular Body-Part Phase Control
Minyue Dai, Ke Fan, Anyi Rao +2
Text-to-motion (T2M) generation is becoming a practical tool for animation and interactive avatars. However, modifying specific body parts while maintaining overall motion coherenc…
OCRA: Object-Centric Learning with 3D and Tactile Priors for Human-to-Robot Action Transfer
Kuanning Wang, Ke Fan, Yuqian Fu +6
We present OCRA, an Object-Centric framework for video-based human-to-Robot Action transfer that learns directly from human demonstration videos to enable robust manipulation. Obje…
Learning Generalizable Hand-Object Tracking from Synthetic Demonstrations
Yinhuai Wang, Runyi Yu, Hok Wai Tsui +9
We present a system for learning generalizable hand-object tracking controllers purely from synthetic data, without requiring any human demonstrations. Our approach makes two key c…
UniTracker: Learning Universal Whole-Body Motion Tracker for Humanoid Robots
Kangning Yin, Weishuai Zeng, Ke Fan +7
Achieving expressive and generalizable whole-body motion control is essential for deploying humanoid robots in real-world environments. In this work, we propose UniTracker, a three…
Towards Synthesized and Editable Motion In-Betweening Through Part-Wise Phase Representation
Minyue Dai, Ke Fan, Bin Ji +5
Styled motion in-betweening is crucial for computer animation and gaming. However, existing methods typically encode motion styles by modeling whole-body motions, often overlooking…
MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space
Lixing Xiao, Shunlin Lu, Huaijin Pi +7
This paper addresses the challenge of text-conditioned streaming motion generation, which requires us to predict the next-step human pose based on variable-length historical motion…