English

A Diffusion Approach to Radiance Field Relighting using Multi-Illumination Synthesis

Computer Vision and Pattern Recognition 2024-09-18 v2 Graphics

Abstract

Relighting radiance fields is severely underconstrained for multi-view data, which is most often captured under a single illumination condition; It is especially hard for full scenes containing multiple objects. We introduce a method to create relightable radiance fields using such single-illumination data by exploiting priors extracted from 2D image diffusion models. We first fine-tune a 2D diffusion model on a multi-illumination dataset conditioned by light direction, allowing us to augment a single-illumination capture into a realistic -- but possibly inconsistent -- multi-illumination dataset from directly defined light directions. We use this augmented data to create a relightable radiance field represented by 3D Gaussian splats. To allow direct control of light direction for low-frequency lighting, we represent appearance with a multi-layer perceptron parameterized on light direction. To enforce multi-view consistency and overcome inaccuracies we optimize a per-image auxiliary feature vector. We show results on synthetic and real multi-view data under single illumination, demonstrating that our method successfully exploits 2D diffusion model priors to allow realistic 3D relighting for complete scenes. Project site https://repo-sam.inria.fr/fungraph/generative-radiance-field-relighting/

Keywords

Cite

@article{arxiv.2409.08947,
  title  = {A Diffusion Approach to Radiance Field Relighting using Multi-Illumination Synthesis},
  author = {Yohan Poirier-Ginter and Alban Gauthier and Julien Philip and Jean-Francois Lalonde and George Drettakis},
  journal= {arXiv preprint arXiv:2409.08947},
  year   = {2024}
}

Comments

Project site https://repo-sam.inria.fr/fungraph/generative-radiance-field-relighting/

R2 v1 2026-06-28T18:43:54.973Z