3 papers
cs.CV2025
PhysiInter: Integrating Physical Mapping for High-Fidelity Human Interaction Generation
Wei Yao, Yunlian Sun, Chang Liu +2
Driven by advancements in motion capture and generative artificial intelligence, leveraging large-scale MoCap datasets to train generative models for synthesizing diverse, realisti…
cs.CV2025
HOSIG: Full-Body Human-Object-Scene Interaction Generation with Hierarchical Scene Perception
Wei Yao, Yunlian Sun, Hongwen Zhang +2
Generating high-fidelity full-body human interactions with dynamic objects and static scenes remains a critical challenge in computer graphics and animation. Existing methods for h…
cs.GR2025
ReCoM: Realistic Co-Speech Motion Generation with Recurrent Embedded Transformer
Yong Xie, Yunlian Sun, Hongwen Zhang +2
We present ReCoM, an efficient framework for generating high-fidelity and generalizable human body motions synchronized with speech. The core innovation lies in the Recurrent Embed…