A Diffusion Approach to Radiance Field Relighting using Multi-Illumination Synthesis
This addresses the challenge of creating relightable 3D scenes from limited data for applications in computer graphics and vision, though it is incremental as it builds on existing diffusion and radiance field techniques.
The paper tackles the problem of relighting radiance fields from single-illumination multi-view data, which is underconstrained for full scenes, by using a method that fine-tunes a 2D diffusion model to synthesize multi-illumination data and optimizes a 3D Gaussian splat representation with an MLP for light direction control, achieving realistic 3D relighting results on synthetic and real data.
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/