GaRe: Relightable 3D Gaussian Splatting for Outdoor Scenes from Unconstrained Photo Collections
Contributions: โข We propose a novel visibility extraction method by applying binary clustering to the residuals between globally illuminated images and ambient-only rendered counterparts, achieving precise separation of direct sunlight effects.
โข We introduce a region-based supervision framework with a structural consistency loss for physically interpretable and coherent illumination decomposition.
โข We integrate ray tracing into Gaussian representations and design a shadow baking process, achieving real-time relighting with single-pass efficiency.