Nabla-R2D3 aligns 3D-native diffusion models with human preferences by backpropagating multi-view 2D reward gradients through the denoising process, improving reward without destroying the pretrained 3D prior.
PixArt- Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation
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.GR 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Nabla-R2D3: Effective and Efficient 3D Diffusion Alignment with 2D Rewards
Nabla-R2D3 aligns 3D-native diffusion models with human preferences by backpropagating multi-view 2D reward gradients through the denoising process, improving reward without destroying the pretrained 3D prior.