6 papers
Retrieving and Refining Winning Noise Tickets for Diffusion-Based Motion Generation
Sakuya Ota, Qing Yu, Kent Fujiwara +2
Diffusion-based text-to-motion models synthesize realistic human motions but often exhibit semantic drift from the input text. Motion is inherently temporal, especially in composit…
ARMS: Anchor-Relational Motion Streaming for Seamless Solo-Social Motion Transitions
Huakun Liu, Qing Yu, Kent Fujiwara +2
Generating temporally continuous and socially coherent human motion from text remains a fundamental challenge, particularly in realistic streams where people act alone, enter inter…
InterCMDM: Block-Causal Diffusion for Autoregressive Human Interaction Generation
Qing Yu, Kent Fujiwara
Text-conditioned human interaction generation must capture both long-range temporal causality within each individual and tightly coupled coordination between partners. Existing int…
ProjFlow: Projection Sampling with Flow Matching for Zero-Shot Exact Spatial Motion Control
Akihisa Watanabe, Qing Yu, Edgar Simo-Serra +1
Generating human motion with precise spatial control is a challenging problem. Existing approaches often require task-specific training or slow optimization, and enforcing hard con…
Causal Motion Diffusion Models for Autoregressive Motion Generation
Qing Yu, Akihisa Watanabe, Kent Fujiwara
Recent advances in motion diffusion models have substantially improved the realism of human motion synthesis. However, existing approaches either rely on full-sequence diffusion mo…
PINO: Person-Interaction Noise Optimization for Long-Duration and Customizable Motion Generation of Arbitrary-Sized Groups
Sakuya Ota, Qing Yu, Kent Fujiwara +2
Generating realistic group interactions involving multiple characters remains challenging due to increasing complexity as group size expands. While existing conditional diffusion m…