Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation

A diffusion model learns to predict a vector field of gradients. We propose to apply chain rule on the learned gradients, and back-propagate the score of a diffusion model through the Jacobian of a differentiable renderer, which we instantiate to be a voxel radiance field.

Data and Resources

Cite this as

Haochen Wang, Xiaodan Du, Jiahao Li, Raymond A. Yeh, Greg Shakhnarovich (2024). Dataset: Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation. https://doi.org/10.57702/tkp1s5ez

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.2212.00774
Author Haochen Wang
More Authors
Xiaodan Du
Jiahao Li
Raymond A. Yeh
Greg Shakhnarovich
Homepage https://arxiv.org/abs/2209.14988