MDM is a classifier-free diffusion model that generates expressive human motions by predicting clean samples rather than noise, supporting text and action conditioning and outperforming prior methods on standard benchmarks.
Text2gestures: A transformer-based network for generating emotive body ges- tures for virtual agents
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2022 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Human Motion Diffusion Model
MDM is a classifier-free diffusion model that generates expressive human motions by predicting clean samples rather than noise, supporting text and action conditioning and outperforming prior methods on standard benchmarks.