Inter-Reflective Gaussian Splatting for Robust and Efficient Inverse Rendering

2026-07-24

AI Summary

Traditional Gaussian splatting methods struggle to support secondary ray queries, limiting their ability to accurately model indirect illumination and interreflections, thereby compromising the physical realism of inverse rendering. This work proposes IRGS++, a novel framework that, for the first time, incorporates physically accurate interreflection transport into Gaussian-based inverse rendering. By leveraging surface-oriented Gaussian primitives, IRGS++ enables differentiable 2D Gaussian ray tracing to solve the full rendering equation—including interreflections—in real time. Coupled with a metallicity-aware material model and robust reflection initialization, the method effectively handles glossy, specular, and metallic surfaces. Evaluated on both low-gloss and glossy datasets, IRGS++ achieves superior material decomposition and relighting quality, demonstrating high physical consistency, accuracy, and efficiency in real-world scenes.

Abstract

Faithful inverse rendering requires visibility and indirect radiance to explain secondary illumination and inter-reflection, yet rasterization-oriented Gaussian representations do not naturally support the secondary-ray queries needed to recover them. We present IRGS++ (Inter-Reflective Gaussian Splatting), a unified robust and efficient Gaussian inverse rendering framework. During transport-aware optimization, IRGS++ employs differentiable 2D Gaussian ray tracing on surface-oriented Gaussian primitives to query visibility and indirect radiance on the fly and evaluate the full rendering equation for inter-reflective transport. This physical core makes Gaussian inverse rendering physically grounded beyond rasterized appearance modeling. To make this backbone useful beyond low-gloss dielectric scenes, the framework incorporates metallic-aware material modeling and robust reflective initialization for glossy, specular, and metallic materials. To make it practical, multiple importance sampling and denoising stabilize finite-sample rendering, while mesh-based secondary-attribute queries reduce the cost of relighting under novel illumination. Quantitative evaluations on low-gloss and glossy benchmarks show improved decomposition and relighting quality together with favorable quality--speed trade-offs under the reported configurations, while real-world studies illustrate plausible relighting under novel illumination.

Problem

• inverse rendering
• inter-reflection
• Gaussian splatting
• indirect radiance
• secondary illumination

Innovation

• Inter-Reflective Gaussian Splatting
• Differentiable Ray Tracing
• Inverse Rendering
• Physically-Based Rendering
• Relighting