FlexMotion reports a latent diffusion model with a physics-aware multimodal autoencoder and a ControlNet-style module for controlling joint locations, contact forces, joint actuations, and muscle activations in generated human motion.
Mofusion: A framework for denoising-diffusion-based motion synthesis
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
FlexMotion: Lightweight, Physics-Aware, and Controllable Human Motion Generation
FlexMotion reports a latent diffusion model with a physics-aware multimodal autoencoder and a ControlNet-style module for controlling joint locations, contact forces, joint actuations, and muscle activations in generated human motion.