Institution profile

Oregon State University

Academic institutionnorthamerica · us
Official website
Research library282linked papers
Opportunities0open roles
Selected work

Representative Papers

Generating Physically Realistic and Directable Human Motions from Multi-modal Inputs

Feb 08, 2025European Conference on Computer Vision

This work addresses the challenge of generating physically plausible and interactively controllable human motion under multimodal weak supervision. We propose the first end-to-end framework that jointly models diverse conditional signals—including text, speech, keyframes, and sketches—while enforcing rigid-body dynamics constraints. Methodologically, we integrate diffusion modeling for spatiotemporal synthesis, incorporate a differentiable neural physics engine to ensure dynamic feasibility, employ cross-modal attention for semantic alignment across modalities, and adopt latent-space disentanglement to enable fine-grained control and real-time editing. Evaluated on HumanML3D, KIT-Motion, and our newly introduced MultiMoCap benchmark, our approach achieves a 32% reduction in FID, a 27% decrease in MPJPE, a 41% improvement in user-controllability scores, and interactive response latency at the millisecond level.

1 citationsRead paper
Recent publications

Latest Papers