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.
Generating diverse and natural 3d human motions from text
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 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.