SGS-Intrinsic: Semantic-Invariant Gaussian Splatting for Sparse-View Indoor Inverse Rendering

TL;DR

SGS-Intrinsic introduces a novel indoor inverse rendering framework that achieves high-quality geometry, material, and illumination disentanglement from sparse-view images, outperforming existing methods.

Contribution

It constructs a dense Gaussian semantic field with priors and combines hybrid illumination and material models for robust inverse rendering.

Findings

Improves geometry reconstruction in sparse-view settings.

Enhances material and illumination disentanglement accuracy.

Outperforms existing 3D Gaussian Splatting methods on benchmarks.

Abstract

We present SGS-Intrinsic, an indoor inverse rendering framework that works well for sparse-view images. Unlike existing 3D Gaussian Splatting (3DGS) based methods that focus on object-centric reconstruction and fail to work under sparse view settings, our method allows to achieve high-quality geometry reconstruction and accurate disentanglement of material and illumination. The core idea is to construct a dense and geometry-consistent Gaussian semantic field guided by semantic and geometric priors, providing a reliable foundation for subsequent inverse rendering. Building upon this, we perform material-illumination disentanglement by combining a hybrid illumination model and material prior to effectively capture illumination-material interactions. To mitigate the impact of cast shadows and enhance the robustness of material recovery, we introduce illumination-invariant material constraint together with a deshadowing model. Extensive experiments on benchmark datasets show that our method consistently improves both reconstruction fidelity and inverse rendering quality over existing 3DGS-based inverse rendering approaches. Our code is available at https://github.com/GrumpySloths/SGS_Intrinsic.github.io.