Research map / 3D vision / Gaussian splatting
RoDUS: Robust Decomposition of Static and Dynamic Elements in Urban Scenes
Thang-Anh-Quan Nguyen, Luis G Roldao Jimenez, Nathan Piasco, Moussab Bennehar, 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 |
|---|---|---|---|
| Use RoDUS instead of EmerNeRF for dynamic object segmentation | RoDUS · KITTI-360 motion segmentation | IoU: 12.56 -> 64.84 | Improved |
| Use RoDUS instead of EmerNeRF for static novel view synthesis | RoDUS · KITTI-360 static NVS | PSNR: 20.59 -> 23.43 | Improved |
| Use RoDUS instead of EmerNeRF | RoDUS · Pandaset static NVS | PSNR: 27.47 -> 25.83 | Hurt |
| Use RoDUS instead of SUDS for full image reconstruction PSNR | RoDUS · KITTI-360 image reconstruction | PSNR: 28.16 -> 26.47 | Hurt |
| Add robust-loss initialization, sky loss and road planar loss (ablation) | RoDUS · KITTI-360/Pandaset ablation | static quality | Improved |
| Add foreground-only mask on dynamic semantic head (ablation) | RoDUS · Qualitative | decomposition | Improved |
| Raise robust-kernel threshold from 0.7 to 0.9 (RobustNeRF) (ablation) | RobustNeRF · Qualitative | static quality | Mixed |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.
- EmerNeRF — EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision (ICLR 2024) · better on 4 of 5 shared results
- SUDS — SUDS: Scalable Urban Dynamic Scenes (CVPR 2023) · better on 1 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
- Multi-Level Neural Scene Graphs for Dynamic Urban Environments (CVPR 2024 · similarity 0.86)
- DynamicCity: Large-Scale 4D Occupancy Generation from Dynamic Scenes (ICLR 2025 · similarity 0.85)
- Dynamic 3D Gaussian Fields for Urban Areas (NeurIPS 2024 · similarity 0.85)
- Entity-NeRF: Detecting and Removing Moving Entities in Urban Scenes (CVPR 2024 · similarity 0.85)
- Flux4D: Flow-based Unsupervised 4D Reconstruction (NeurIPS 2025 · similarity 0.85)
- STORM: Spatio-TempOral Reconstruction Model For Large-Scale Outdoor Scenes (ICLR 2025 · similarity 0.85)
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.
