Learning a Diffusion Prior for NeRFs
This addresses the challenge of under-constrained NeRF training for 3D scene representation, but it is incremental as it applies an existing diffusion method to a new domain.
The paper tackles the problem of generating Neural Radiance Fields (NeRFs) with limited supervision by learning a diffusion prior, enabling realistic sampling and conditional generation from sparse views.
Neural Radiance Fields (NeRFs) have emerged as a powerful neural 3D representation for objects and scenes derived from 2D data. Generating NeRFs, however, remains difficult in many scenarios. For instance, training a NeRF with only a small number of views as supervision remains challenging since it is an under-constrained problem. In such settings, it calls for some inductive prior to filter out bad local minima. One way to introduce such inductive priors is to learn a generative model for NeRFs modeling a certain class of scenes. In this paper, we propose to use a diffusion model to generate NeRFs encoded on a regularized grid. We show that our model can sample realistic NeRFs, while at the same time allowing conditional generations, given a certain observation as guidance.