Research map / 3D vision / Gaussian splatting
DeGauss: Dynamic-Static Decomposition with Gaussian Splatting for Distractor-free 3D Reconstruction
Rui Wang, Quentin Lohmeyer, Mirko Meboldt, Siyu Tang
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 brightness control (BC) (ablation) | DeGauss · NeRF On-the-go | PSNR: 23.54 -> 23.91 | Improved |
| add partial opacity reset (POR) (ablation) | DeGauss · NeRF On-the-go | PSNR: 23.56 -> 23.91 | Improved |
| add depth loss L_depth (ablation) | DeGauss · NeRF On-the-go | PSNR: 23.68 -> 23.91 | Improved |
| add background mask element m_b' (ablation) | DeGauss · NeRF On-the-go | PSNR: 23.83 -> 23.91 | Improved |
| add brightness control (BC) (ablation) | DeGauss · NeRF On-the-go | LPIPS: 0.118 -> 0.113 | Improved |
| add background mask element m_b' (ablation) | DeGauss · NeRF On-the-go | LPIPS: 0.115 -> 0.113 | Improved |
| add depth loss L_depth (ablation) | DeGauss · NeRF On-the-go | LPIPS: 0.113 -> 0.113 | No clear effect |
| raise densify gradient threshold x2 | DeGauss · Neu3D | FPS: 71 -> 157 | Improved |
| raise densify gradient threshold x2 | 4DGS · Neu3D | PSNR: 31.12 -> 28.72 | Hurt |
| raise densify gradient threshold x2 | DeGauss · Neu3D | PSNR: 31.52 -> 31.56 | No clear effect |
| decoupled foreground/background Gaussians vs 4DGS | DeGauss · Neu3D | LPIPS: 0.058 -> 0.047 | Improved |
| decoupled foreground/background Gaussians vs SpotlessSplats | DeGauss · NeRF On-the-go | LPIPS: 0.145 -> 0.113 | Improved |
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.
- DeSplat — DeSplat: Decomposed Gaussian Splatting for Distractor-Free Rendering (CVPR 2025) · better on 3 of 3 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
- HiCoM: Hierarchical Coherent Motion for Dynamic Streamable Scenes with 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.90)
- DeSplat: Decomposed Gaussian Splatting for Distractor-Free Rendering (CVPR 2025 · similarity 0.89)
- DGS-LRM: Real-Time Deformable 3D Gaussian Reconstruction From Monocular Videos (NeurIPS 2025 · similarity 0.89)
- Swift4D: Adaptive divide-and-conquer Gaussian Splatting for compact and efficient reconstruction of dynamic scene (ICLR 2025 · similarity 0.89)
- Learning Efficient Fuse-and-Refine for Feed-Forward 3D Gaussian Splatting (NeurIPS 2025 · similarity 0.89)
- MaskGaussian: Adaptive 3D Gaussian Representation from Probabilistic Masks (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.
