Research map / 3D vision / Gaussian splatting
Through the Water: Refractive Gaussian Splatting for Water Surface Scenes
Yeonghun Yoon, Hojoon Jung, Jaeyoon Lee, Taegwan Kim, Gyuhyun Kim, Jongwon Choi
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 |
|---|---|---|---|
| model refraction with WSGS vs 3DGS | 3DGS · Water Synthetic pool (water region) | PSNR: 26.496 -> 34.632 | Improved |
| model refraction with WSGS vs 3DGS | 3DGS · Water Real fishbowl (water region) | PSNR: 25.235 -> 31.626 | Improved |
| WSGS vs 3DGS on whole image | 3DGS · Water Real bucket (entire image) | PSNR: 36.939 -> 36.534 | Hurt |
| WSGS vs 3DGS on whole image | 3DGS · Water Real basin (entire image) | PSNR: 33.160 -> 33.942 | Improved |
| WSGS vs 3DGS on Water Real fishbowl | 3DGS · Water Real fishbowl (entire image) | PSNR: 31.760 -> 33.492 | Improved |
| add trainable water plane (ablation) | WSGS · Water Synthetic basin + Water Real fishbowl | PSNR: 30.121 -> 35.817 | Improved |
| add soft mask (ablation) | WSGS · Water Synthetic basin + Water Real fishbowl | PSNR: 31.124 -> 35.817 | Improved |
| add pseudo mask loss (ablation) | WSGS · Water Synthetic basin + Water Real fishbowl | PSNR: 35.785 -> 35.817 | No clear effect |
| add pseudo mask loss (ablation) | WSGS · Non-water region | PSNR: 17.604 -> 30.267 | Improved |
| shift plane height by 5 percent or change mask weight 0.05 to 0.03/0.07 (ablation) | WSGS · basin, fishbowl | PSNR: basin 38.099±0.05; fishbowl 33.466±0.08 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- EnvGS — EnvGS: Modeling View-Dependent Appearance with Environment Gaussian (CVPR 2025) · better on 7 of 7 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
- Subsurface Scattering for Gaussian Splatting (NeurIPS 2024 · similarity 0.90)
- Reflective Gaussian Splatting (ICLR 2025 · similarity 0.89)
- IRGS: Inter-Reflective Gaussian Splatting with 2D Gaussian Ray Tracing (CVPR 2025 · similarity 0.87)
- MaterialRefGS: Reflective Gaussian Splatting with Multi-view Consistent Material Inference (NeurIPS 2025 · similarity 0.87)
- Gaussian Splashing: Unified Particles for Versatile Motion Synthesis and Rendering (CVPR 2025 · similarity 0.87)
- DoF-Gaussian: Controllable Depth-of-Field for 3D Gaussian Splatting (CVPR 2025 · similarity 0.87)
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.
