GI-GS: Global Illumination Decomposition on Gaussian Splatting for Inverse Rendering
Hongze Chen, Zehong Lin, Jun Zhang
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.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext fbb6a656-135b-4eff-8f15-12b769ff7ceaCited by top-tier papers15
- MV-CoLight: Efficient Object Compositing with Consistent Lighting and Shadow GenerationKerui Ren, Jiayang Bai, Linning Xu, Lihan Jiang et al.NeurIPS 2025 · 9 citations
- LuxRemix: Lighting Decomposition and Remixing for Indoor ScenesRuofan Liang, Norman Müller, Ethan Weber, Duncan Zauss et al.CVPR 2026 · 7 citations
- RT-Splatting: Joint Reflection-Transmission Modeling with Gaussian SplattingJi Shi, Xianghua Ying, Bowei Xing, Ruohao Guo et al.CVPR 2026 · 2 citations
- MatSpray: Fusing 2D Material World Knowledge on 3D GeometryPhilipp Langsteiner, Jan-Niklas Dihlmann, Hendrik P. A. LenschCVPR 2026 · 2 citations
- Radiometrically Consistent Gaussian Surfels for Inverse RenderingKyu Beom Han, Jaeyoon Kim, Woo Jae Kim, Jinhwan Seo et al.ICLR 2026 · 2 citations
Builds on21
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 5,687 citations
- Instant neural graphics primitives with a multiresolution hash encodingThomas Müller, Alex Evans, Christoph Schied, Alexander KellerSIGGRAPH 2022 · 4,089 citations
- Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance FieldsJonathan T. Barron, Ben Mildenhall, Matthew Tancik, Peter Hedman et al.ICCV 2021 · 2,700 citations
- NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view ReconstructionPeng Wang, Lingjie Liu, Yuan Liu, Christian Theobalt et al.NeurIPS 2021 · 2,500 citations
- Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance FieldsJonathan T. Barron, Ben Mildenhall, Dor Verbin, Pratul P. Srinivasan et al.CVPR 2022 · 1,603 citations
Related papers
- RTR-GS: 3D Gaussian Splatting for Inverse Rendering with Radiance Transfer and ReflectionYongyang Zhou, Fanglue Zhang, Zichen Wang, Lei ZhangACM MM 2025 · 4 citations
- GS-IR: 3D Gaussian Splatting for Inverse RenderingZhihao Liang, Qi Zhang, Ying Feng, Ying Shan et al.CVPR 2024
- GHPT: Real-Time Relightable Gaussian Splatting using Hybrid Path TracingJinyang Bo, Fan Dou, Wenrui Quan, Shangxun Liu et al.CVPR 2026
- MaterialRefGS: Reflective Gaussian Splatting with Multi-view Consistent Material InferenceWenyuan Zhang, Jimin Tang, Weiqi Zhang, Yi Fang et al.NeurIPS 2025 · 25 citations
- Reflective Gaussian SplattingYuxuan Yao, Zixuan Zeng, Chun Gu, Xiatian Zhu et al.ICLR 2025
