SGS-Intrinsic: Semantic-Invariant Gaussian Splatting for Sparse-View Indoor Inverse Rendering
This work addresses the challenge of indoor scene reconstruction from limited views, which is incremental as it builds upon 3D Gaussian Splatting with semantic and geometric priors.
The authors tackled the problem of sparse-view indoor inverse rendering by developing SGS-Intrinsic, which achieved high-quality geometry reconstruction and accurate material-illumination disentanglement, outperforming existing 3DGS-based methods on benchmark datasets.
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.