GI-GS: Global Illumination Decomposition on Gaussian Splatting for Inverse Rendering

TL;DR

GI-GS introduces a novel inverse rendering framework that combines 3D Gaussian Splatting with path tracing and deferred shading to accurately model global illumination, enabling realistic relighting and view synthesis.

Contribution

It proposes a new method for inverse rendering that accurately models indirect lighting using path tracing within a Gaussian Splatting framework, surpassing previous approaches.

Findings

Outperforms existing methods in rendering quality.

Achieves efficient and realistic relighting.

Provides superior novel view synthesis results.

Abstract

We present GI-GS, a novel inverse rendering framework that leverages 3D Gaussian Splatting (3DGS) and deferred shading to achieve photo-realistic novel view synthesis and relighting. In inverse rendering, accurately modeling the shading processes of objects is essential for achieving high-fidelity results. Therefore, it is critical to incorporate global illumination to account for indirect lighting that reaches an object after multiple bounces across the scene. Previous 3DGS-based methods have attempted to model indirect lighting by characterizing indirect illumination as learnable lighting volumes or additional attributes of each Gaussian, while using baked occlusion to represent shadow effects. These methods, however, fail to accurately model the complex physical interactions between light and objects, making it impossible to construct realistic indirect illumination during relighting. To address this limitation, we propose to calculate indirect lighting using efficient path tracing with deferred shading. In our framework, we first render a G-buffer to capture the detailed geometry and material properties of the scene. Then, we perform physically-based rendering (PBR) only for direct lighting. With the G-buffer and previous rendering results, the indirect lighting can be calculated through a lightweight path tracing. Our method effectively models indirect lighting under any given lighting conditions, thereby achieving better novel view synthesis and competitive relighting. Quantitative and qualitative results show that our GI-GS outperforms existing baselines in both rendering quality and efficiency.