Text-conditioned 3D human generation is achieved by distilling a 2D-supervised GAN's triplane space into a text-conditioned diffusion model, avoiding 3D supervision and test-time optimization.
Learning representations and generative models for 3d point clouds
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
-
GANFusion: Feed-Forward Text-to-3D with Diffusion in GAN Space
Text-conditioned 3D human generation is achieved by distilling a 2D-supervised GAN's triplane space into a text-conditioned diffusion model, avoiding 3D supervision and test-time optimization.