Research map / 3D vision / Gaussian splatting
Gaussian Mapping for Evolving Scenes
Vladimir Yugay, Thies Kersten, Luca Carlone, Theo Gevers, Martin R. Oswald, Lukas Schmid
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 dynamic scene adaptation (Add and Remove) to the mapper (ablation) | GaME · Flat (input views) | PSNR (dB): 21.25 -> 24.55 | Improved |
| add dynamic scene adaptation (Add and Remove) to the mapper (ablation) | GaME · Flat (input views) | Depth L1 (cm): 29.20 -> 6.9 | Improved |
| combine Remove with Add instead of Remove only (ablation) | GaME DSA · Flat (input views) | PSNR (dB): 24.13 -> 24.55 | Improved |
| mask only stale regions in keyframes instead of keeping all keyframes (ablation) | GaME · Flat (input views) | PSNR (dB): 23.57 -> 24.55 | Improved |
| mask only stale regions in keyframes instead of keeping all keyframes (ablation) | GaME · Flat (input views) | Depth L1 (cm): 6.70 -> 6.9 | No clear effect |
| discard whole stale keyframes instead of masking stale regions (ablation) | GaME · Flat (input views) | PSNR (dB): 24.55 -> 13.72 | Hurt |
| discard whole stale keyframes instead of masking stale regions (ablation) | GaME · Flat (input views) | Depth L1 (cm): 6.9 -> 764.40 | Hurt |
| use estimated camera poses instead of ground-truth poses (ablation) | GaME · Aria room0 (input views) | PSNR (dB): 31.54 -> 31.45 | No clear effect |
| add final refinement after incremental mapping (ablation) | GaME · Flat (input views) | PSNR (dB): 23.70 -> 24.55 | Improved |
| add final refinement after incremental mapping (ablation) | GaME · Flat (input views) | Depth L1 (cm): 7.2 -> 7.9 | Hurt |
| vary epsilon_depth, epsilon_color, epsilon_opacity by up to 20 percent (ablation) | GaME · Aria room0 | PSNR (dB): std dev 0.21, 0.14, 0.11 | No clear effect |
| use GaME on static scenes instead of SplaTAM | GaME · TUM-RGBD (average, input views) | PSNR (dB): 21.19 -> 20.63 | No clear effect |
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.
- SplaTAM — SplaTAM: Splat Track & Map 3D Gaussians for Dense RGB-D SLAM (CVPR 2024) · better on 4 of 5 shared results
- DG-SLAM — DG-SLAM: Robust Dynamic Gaussian Splatting SLAM with Hybrid Pose Optimization (NeurIPS 2024) · better on 2 of 2 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
- Swift4D: Adaptive divide-and-conquer Gaussian Splatting for compact and efficient reconstruction of dynamic scene (ICLR 2025 · similarity 0.89)
- Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction (CVPR 2024 · similarity 0.89)
- SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes (CVPR 2024 · similarity 0.88)
- Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesis (CVPR 2024 · similarity 0.88)
- FreeTimeGS: Free Gaussian Primitives at Anytime Anywhere for Dynamic Scene Reconstruction (CVPR 2025 · similarity 0.88)
- ActiveGAMER: Active GAussian Mapping through Efficient Rendering (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.
