Research map / 3D vision / Gaussian splatting
UV-RGS: Relightable 3D Gaussian Splatting from Unposed Views Under Varied Illuminations
Wei Feng, Chi Huang, Qi Zhang, Qian Zhang, Nan Li
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 viewpoint dividing (VD) (ablation) | UV-RGS · NeRF-OSR relighting | PSNR: 17.55 -> 19.96 | Improved |
| add viewpoint dividing (VD) (ablation) | UV-RGS · NeRF-OSR relighting | SSIM: 0.616 -> 0.758 | Improved |
| add viewpoint dividing (VD) (ablation) | UV-RGS · NeRF-OSR relighting | LPIPS: 0.477 -> 0.339 | Improved |
| add constituent model learning (CML) after VD (ablation) | UV-RGS · NeRF-OSR relighting | PSNR: 19.96 -> 20.35 | Improved |
| add constituent model learning (CML) after VD (ablation) | UV-RGS · NeRF-OSR relighting | SSIM: 0.758 -> 0.740 | Hurt |
| add constituent model learning (CML) after VD (ablation) | UV-RGS · NeRF-OSR relighting | LPIPS: 0.339 -> 0.328 | Improved |
| add holistic model learning (HML) (ablation) | UV-RGS · NeRF-OSR relighting | PSNR: 20.35 -> 21.69 | Improved |
| add holistic model learning (HML) (ablation) | UV-RGS · NeRF-OSR relighting | SSIM: 0.740 -> 0.884 | Improved |
| add holistic model learning (HML) (ablation) | UV-RGS · NeRF-OSR relighting | LPIPS: 0.328 -> 0.208 | Improved |
| use UV-RGS instead of SFGS for pose estimation | UV-RGS · NeRF-OSR pose estimation | RPE_R: 1.392 -> 1.073 | Improved |
| use UV-RGS instead of SVG-IR | UV-RGS · TensoIR Synthetic NVS | PSNR: 29.90 -> 31.95 | Improved |
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.
- SVG-IR — SVG-IR: Spatially-Varying Gaussian Splatting for Inverse Rendering (CVPR 2025) · better on 7 of 7 shared results
- GSIR — GS-IR: 3D Gaussian Splatting for Inverse Rendering (CVPR 2024) · better on 6 of 6 shared results
- GGRT — GGRt: Towards Generalizable 3D Gaussians without Pose Priors in Real-Time (ECCV 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
- MetaGS: A Meta-Learned Gaussian-Phong Model for Out-of-Distribution 3D Scene Relighting (NeurIPS 2025 · similarity 0.92)
- UVGS: Reimagining Unstructured 3D Gaussian Splatting using UV Mapping (CVPR 2025 · similarity 0.90)
- SVG-IR: Spatially-Varying Gaussian Splatting for Inverse Rendering (CVPR 2025 · similarity 0.90)
- GI-GS: Global Illumination Decomposition on Gaussian Splatting for Inverse Rendering (ICLR 2025 · similarity 0.90)
- RNG: Relightable Neural Gaussians (CVPR 2025 · similarity 0.89)
- GS-IR: 3D Gaussian Splatting for Inverse Rendering (CVPR 2024 · 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.
