PINO sequentially composes pairwise interactions and optimizes diffusion noise with overlap and control penalties to generate customizable, artifact-reduced group motion for arbitrary group sizes.
Freemotion: A unified framework for number- free text-to-motion synthesis
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
PINO: Person-Interaction Noise Optimization for Long-Duration and Customizable Motion Generation of Arbitrary-Sized Groups
PINO sequentially composes pairwise interactions and optimizes diffusion noise with overlap and control penalties to generate customizable, artifact-reduced group motion for arbitrary group sizes.