A latent-space GAN achieves FID 0.482 on HumanML3D text-to-motion, close to latent diffusion (0.473) at a fraction of the inference FLOPs.
Synthesis of compositional animations from textual descriptions
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
LS-GAN: Human Motion Synthesis with Latent-space GANs
A latent-space GAN achieves FID 0.482 on HumanML3D text-to-motion, close to latent diffusion (0.473) at a fraction of the inference FLOPs.