Research map / 3D vision / Gaussian splatting
SGS-Intrinsic: Semantic-Invariant Gaussian Splatting for Sparse-View Indoor Inverse Rendering
Jiahao Niu, Rongjia Zheng, Wenju Xu, Wei-Shi Zheng, Qing Zhang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add normal prior loss (ablation) | SGS-Intrinsic · Interiorverse (12 views) | Albedo PSNR: 16.90 -> 17.70 | Improved |
| add pseudo-view semantic consistency loss (ablation) | SGS-Intrinsic · Interiorverse (12 views) | Albedo PSNR: 16.80 -> 17.70 | Improved |
| add SGM point lights to environment map (ablation) | SGS-Intrinsic · Interiorverse (12 views) | Albedo PSNR: 14.78 -> 17.70 | Improved |
| add deshadowing module (ablation) | SGS-Intrinsic · Interiorverse (12 views) | Albedo PSNR: 16.22 -> 17.70 | Improved |
| add deshadowing module (ablation) | SGS-Intrinsic · Interiorverse (12 views) | PBR novel view PSNR: 20.71 -> 20.90 | Mixed |
| add relighting consistency loss (ablation) | SGS-Intrinsic · Interiorverse (12 views) | Albedo PSNR: 17.20 -> 17.70 | Improved |
| add multi-view semantic consistency loss (ablation) | SGS-Intrinsic · Interiorverse (12 views) | Albedo PSNR: 17.10 -> 17.70 | Improved |
| add multi-view semantic consistency loss (ablation) | SGS-Intrinsic · Interiorverse (12 views) | PBR novel view PSNR: 20.20 -> 20.90 | Improved |
| perturb Gaussian geometry/normal/semantic priors with noise (ablation) | SGS-Intrinsic · Interiorverse (12 views) | Albedo PSNR: 17.7 -> 17.5 | No clear effect |
| use 200-view GT cameras instead of sparse-view VGGT (ablation) | SGS-Intrinsic · Interiorverse (12 views) | Albedo PSNR: 17.7 -> 17.7 | No clear effect |
| SGS-Intrinsic vs best baseline on real data | SGS-Intrinsic · DL3DV (24 views) | NVS PSNR: 18.98 -> 19.31 | Improved |
| SGS-Intrinsic vs IRGS on PBR novel view SSIM | SGS-Intrinsic · Interiorverse (12 views) | NVS SSIM (PBR): 0.74 -> 0.73 | Mixed |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- SVGIR — SVG-IR: Spatially-Varying Gaussian Splatting for Inverse Rendering (CVPR 2025) · better on 4 of 4 shared results
- IRGS — IRGS: Inter-Reflective Gaussian Splatting with 2D Gaussian Ray Tracing (CVPR 2025) · better on 2 of 2 shared results
- GSIR — GS-IR: 3D Gaussian Splatting for Inverse Rendering (CVPR 2024) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- GS-IR: 3D Gaussian Splatting for Inverse Rendering (CVPR 2024 · similarity 0.91)
- SVG-IR: Spatially-Varying Gaussian Splatting for Inverse Rendering (CVPR 2025 · similarity 0.90)
- MaterialRefGS: Reflective Gaussian Splatting with Multi-view Consistent Material Inference (NeurIPS 2025 · similarity 0.90)
- GI-GS: Global Illumination Decomposition on Gaussian Splatting for Inverse Rendering (ICLR 2025 · similarity 0.90)
- IndoorGS: Geometric Cues Guided Gaussian Splatting for Indoor Scene Reconstruction (CVPR 2025 · similarity 0.90)
- Generative Sparse-View Gaussian Splatting (CVPR 2025 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
