DiLAST optimizes 3D latents via guidance from a 2D diffusion model to enable generalizable style transfer for OOD styles in 3D asset generation.
Autodecoding latent 3d diffusion models.Advances in Neural Information Processing Systems, 36:67021–67047
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Structured 3D Latents Are Surprisingly Powerful: Unleashing Generalizable Style with 2D Diffusion
DiLAST optimizes 3D latents via guidance from a 2D diffusion model to enable generalizable style transfer for OOD styles in 3D asset generation.