Research map / 3D vision / Gaussian splatting
SWAG: Splatting in the Wild images with Appearance-conditioned Gaussians
Hiba Dahmani, Moussab Bennehar, Nathan Piasco, Luis G Roldao Jimenez, Dzmitry Tsishkou
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 appearance embedding and transient Gaussian modeling to 3DGS | 3DGS · Phototourism | PSNR: average margin of 5.01 dB | Improved |
| add appearance embedding and transient Gaussian modeling to 3DGS | 3DGS · NeRF-OSR | PSNR: average PSNR margin of 5 dB | Improved |
| add transient Gaussian detection (ablation) | SWAG-A · Phototourism Trevi Fountain | PSNR: 22.35 -> 23.10 | Improved |
| add transient Gaussian detection (ablation) | SWAG-A · Phototourism Brandenburg Gate | PSNR: 26.44 -> 26.33 | No clear effect |
| add appearance color dependency (ablation) | SWAG-T · Phototourism Sacre Coeur | PSNR: 19.06 -> 21.16 | Improved |
| add appearance color dependency (ablation) | SWAG-T · Phototourism Brandenburg Gate | PSNR: 24.46 -> 26.33 | Improved |
| use SWAG over 3DGS for efficiency | 3DGS · Phototourism mean efficiency | FPS: 181 -> 15.29 | Hurt |
| use SWAG instead of NeRF-based in-the-wild baselines | RefinedFields · Phototourism mean efficiency | train time (h): 150 -> 0.83 | Improved |
Later papers that compared with this method
2 later accepted papers report SWAG as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- GaRe: Relightable 3D Gaussian Splatting for Outdoor Scenes from Unconstrained Photo Collections (ICCV 2025 · better on 4 of 4 shared results)
- WildGaussians: 3D Gaussian Splatting In the Wild (NeurIPS 2024 · better on 5 of 9 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
- FewViewGS: Gaussian Splatting with Few View Matching and Multi-stage Training (NeurIPS 2024 · similarity 0.90)
- COLMAP-Free 3D Gaussian Splatting (CVPR 2024 · similarity 0.90)
- Robust Neural Rendering in the Wild with Asymmetric Dual 3D Gaussian Splatting (NeurIPS 2025 · similarity 0.90)
- Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitives (CVPR 2025 · similarity 0.90)
- MS-GS: Multi-Appearance Sparse-View 3D Gaussian Splatting in the Wild (NeurIPS 2025 · similarity 0.90)
- Splatter Image: Ultra-Fast Single-View 3D Reconstruction (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.
