Research map / 3D vision / Gaussian splatting
GaRe: Relightable 3D Gaussian Splatting for Outdoor Scenes from Unconstrained Photo Collections
Haiyang Bai, Jiaqi Zhu, Songru Jiang, Wei Huang, Tao Lu, Yuanqi Li, Jie Guo, Runze Fu, Yanwen Guo, Lijun Chen
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 |
|---|---|---|---|
| use residual-based visibility extraction instead of coarse preprocessed visibility (ablation) | outdoor scenes · sun visibility map quality | qualitative | Improved |
| add structural consistency loss (SCL) (ablation) | sun shading · shading consistency outside lit regions | qualitative | Improved |
| add sky filter before ray tracing (ablation) | ray-traced visibility · visibility map | qualitative | Improved |
| add front (depth) filter before ray tracing (ablation) | ray-traced visibility · visibility map | qualitative | Improved |
| add sky mask to visibility (ablation) | ray-traced visibility · sky visibility | qualitative | Improved |
| replace per-pixel ray tracing with baked visibility features | GaRe · inference | qualitative | Improved |
| compare GaRe with WildGaussians and GS-W on training time | GaRe · Train hrs | hours: 4.6 vs 7.4 and 6.4 | Improved |
| compare GaRe with 3DGS and SWAG on training time | GaRe · Train hrs | hours: 4.6 vs 2.6 and 3.6 | Hurt |
| compare GaRe with WildGaussians on rendering speed | GaRe · FPS | FPS: 32 vs 108 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- WildGaussians — WildGaussians: 3D Gaussian Splatting In the Wild (NeurIPS 2024) · better on 9 of 10 shared results
- SWAG — SWAG: Splatting in the Wild images with Appearance-conditioned Gaussians (ECCV 2024) · better on 4 of 4 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
- GI-GS: Global Illumination Decomposition on Gaussian Splatting for Inverse Rendering (ICLR 2025 · similarity 0.91)
- MetaGS: A Meta-Learned Gaussian-Phong Model for Out-of-Distribution 3D Scene Relighting (NeurIPS 2025 · similarity 0.90)
- RNG: Relightable Neural Gaussians (CVPR 2025 · similarity 0.89)
- Ref-GS: Directional Factorization for 2D Gaussian Splatting (CVPR 2025 · similarity 0.89)
- MaterialRefGS: Reflective Gaussian Splatting with Multi-view Consistent Material Inference (NeurIPS 2025 · similarity 0.88)
- Luminance-GS: Adapting 3D Gaussian Splatting to Challenging Lighting Conditions with View-Adaptive Curve Adjustment (CVPR 2025 · similarity 0.88)
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.
