Research map / 3D vision / Gaussian splatting
GUS-IR: Gaussian Splatting With Unified Shading for Inverse Rendering
Zhihao Liang, Hongdong Li, Kui Jia, Kailing Guo, Qi 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 deferred shading branch to forward shading (unified shading) (ablation) | GUS-IR forward-only · Glossy Blender | PSNR: 28.64 -> 29.44 | Improved |
| add forward shading branch to deferred-only training (unified shading) (ablation) | GUS-IR deferred-only · TensoIR | PSNR: 36.35 -> 37.61 | Improved |
| add deferred shading to forward-only (ablation) | GUS-IR forward-only · TensoIR | PSNR: 37.74 -> 37.61 | Hurt |
| add deferred shading to forward-only (ablation) | GUS-IR forward-only · Glossy Blender | LPIPS: 0.084 -> 0.057 | Improved |
| add deferred shading to forward-only (ablation) | GUS-IR forward-only · Shiny Blender | PSNR: 33.15 -> 34.28 | Improved |
| use shortest-axis normal instead of attached learnable normal (ablation) | Attach Normal · TensoIR relighting | PSNR: 26.12 -> 27.53 | Improved |
| use shortest-axis normal instead of attached learnable normal (ablation) | Attach Normal · TensoIR | MAE: 5.433 -> 4.485 | Improved |
| use shortest-axis normal instead of residual normal (ablation) | Residual Normal · Glossy Blender relighting | PSNR: 24.72 -> 25.17 | Improved |
| use shortest-axis normal instead of attached normal (ablation) | Attach Normal · Mip-NeRF 360 Outdoor | PSNR: 23.89 -> 23.76 | Hurt |
| add indirect illumination and ambient occlusion modeling (ablation) | GUS-IR without indirect · Mip-NeRF 360 Indoor | PSNR: 28.52 -> 28.98 | Improved |
| add indirect illumination and ambient occlusion modeling (ablation) | GUS-IR without indirect · TensoIR | PSNR: 37.37 -> 37.61 | Improved |
| add indirect illumination and ambient occlusion modeling (ablation) | GUS-IR without indirect · Shiny Blender | MAE: 2.193 -> 2.193 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 4 on most shared results.
- GS-IR — GS-IR: 3D Gaussian Splatting for Inverse Rendering (CVPR 2024) · better on 3 of 3 shared results
- ENVIDR — ENVIDR: Implicit Differentiable Renderer with Neural Environment Lighting (ICCV 2023) · better on 1 of 2 shared results
- Ref-NeRF — Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fields (CVPR 2022) · better on 0 of 2 shared results
- GaussianShader — GaussianShader: 3D Gaussian Splatting with Shading Functions for Reflective Surfaces (CVPR 2024) · better on 1 of 1 shared result
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 0.92)
- SVG-IR: Spatially-Varying Gaussian Splatting for Inverse Rendering (CVPR 2025 · similarity 0.91)
- GI-GS: Global Illumination Decomposition on Gaussian Splatting for Inverse Rendering (ICLR 2025 · similarity 0.90)
- IBGS: Image-Based Gaussian Splatting (NeurIPS 2025 · similarity 0.89)
- Ref-GS: Directional Factorization for 2D Gaussian Splatting (CVPR 2025 · similarity 0.89)
- Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitives (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.
