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. This setup aggregates 2D scores at multiple camera viewpoints into a 3D score, and repurposes a pretrained 2D model for 3D data generation. We identify a technical challenge of distribution mismatch that arises in this application, and propose a novel estimation mechanism to resolve it. We run our algorithm on several off-the-shelf diffusion image generative models, including the recently released Stable Diffusion trained on the large-scale LAION dataset.
@article{arxiv.2212.00774,
title = {Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation},
author = {Haochen Wang and Xiaodan Du and Jiahao Li and Raymond A. Yeh and Greg Shakhnarovich},
journal= {arXiv preprint arXiv:2212.00774},
year = {2022}
}