4 papers
Diversify Diffusion with Temperature Sampling and Variance-Corrective Time Shifting
Peizhuo Li, Emre Aksan, Alexandru-Eugen Ichim +2
Diffusion models faithfully reproduce their training distribution, but also inherit its imbalances and leave rare or under-represented modes hard to reach. A natural inference-time…
Dancing Points: Synthesizing Ballroom Dancing with Three-Point Inputs
Peizhuo Li, Sebastian Starke, Yuting Ye +1
Ballroom dancing is a structured yet expressive motion category. Its highly diverse movement and complex interactions between leader and follower dancers make the understanding and…
WalkTheDog: Cross-Morphology Motion Alignment via Phase Manifolds
Peizhuo Li, Sebastian Starke, Yuting Ye +1
We present a new approach for understanding the periodicity structure and semantics of motion datasets, independently of the morphology and skeletal structure of characters. Unlike…
Neural Garment Dynamics via Manifold-Aware Transformers
Peizhuo Li, Tuanfeng Y. Wang, Timur Levent Kesdogan +2
Data driven and learning based solutions for modeling dynamic garments have significantly advanced, especially in the context of digital humans. However, existing approaches often…