GaRe: Relightable 3D Gaussian Splatting for Outdoor Scenes from Unconstrained Photo Collections

TL;DR

This paper introduces GaRe, a novel 3D Gaussian splatting framework for outdoor scene relighting from unconstrained photos, enabling diverse shading and realistic shadows through innovative decomposition and rendering techniques.

Contribution

GaRe's key innovations include residual sun visibility extraction, region-based supervision with structural consistency, and ray-tracing shadow simulation, advancing outdoor relighting capabilities.

Findings

Achieves competitive view synthesis fidelity.

Enables diverse shading manipulation and dynamic shadows.

Produces more natural and multifaceted illumination effects.

Abstract

We propose a 3D Gaussian splatting-based framework for outdoor relighting that leverages intrinsic image decomposition to precisely integrate sunlight, sky radiance, and indirect lighting from unconstrained photo collections. Unlike prior methods that compress the per-image global illumination into a single latent vector, our approach enables simultaneously diverse shading manipulation and the generation of dynamic shadow effects. This is achieved through three key innovations: (1) a residual-based sun visibility extraction method to accurately separate direct sunlight effects, (2) a region-based supervision framework with a structural consistency loss for physically interpretable and coherent illumination decomposition, and (3) a ray-tracing-based technique for realistic shadow simulation. Extensive experiments demonstrate that our framework synthesizes novel views with competitive fidelity against state-of-the-art relighting solutions and produces more natural and multifaceted illumination and shadow effects.