Research map / 3D vision / Depth and stereo
Dynamic Visual SLAM using a General 3D Prior
Xingguang Zhong, Liren Jin, Marija Popovic, Jens Behley, Cyrill Stachniss
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 moving object mask from pi3_mos (ablation) | patch-based SLAM without depth prior · Bonn | ATE RMSE (cm): 4.82 -> 2.67 | Improved |
| add moving object mask from pi3_mos (ablation) | patch-based SLAM without depth prior · Wild-SLAM MoCap | ATE RMSE (cm): 1.23 -> 0.98 | Improved |
| add moving mask to depth prior and uncertainty BA (ablation) | SLAM with depth prior · Bonn | ATE RMSE (cm): 3.91 -> 2.20 | Improved |
| add moving mask to depth prior and uncertainty BA (ablation) | SLAM with depth prior · Wild-SLAM MoCap | ATE RMSE (cm): 3.78 -> 0.42 | Improved |
| add fixed-weight depth prior (ablation) | SLAM with moving mask · Bonn | ATE RMSE (cm): 2.67 -> 2.52 | Improved |
| add fixed-weight depth prior (ablation) | SLAM with moving mask · Wild-SLAM MoCap | ATE RMSE (cm): 0.98 -> 0.82 | Improved |
| add uncertainty-aware BA weighting (ablation) | SLAM with moving mask and depth prior · Bonn | ATE RMSE (cm): 2.52 -> 2.20 | Improved |
| add uncertainty-aware BA weighting (ablation) | SLAM with moving mask and depth prior · Wild-SLAM MoCap | ATE RMSE (cm): 0.82 -> 0.42 | Improved |
| add depth prior and uncertainty BA without moving mask (ablation) | patch-based SLAM · Wild-SLAM MoCap | ATE RMSE (cm): 1.23 -> 3.78 | Hurt |
| add depth prior and uncertainty BA without moving mask (ablation) | patch-based SLAM · Bonn | ATE RMSE (cm): 4.82 -> 3.91 | Improved |
| use pi3_mos masks instead of Easi3R (MonST3R) masks | moving object segmentation · DAVIS-17 | JM: 56.5 -> 70.6 | Improved |
| use the SLAM system rather than WildGS-SLAM on fast camera motion | camera tracking · Sintel | ATE (cm): 18.2 -> 1.9 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 on most shared results.
- WildGS-SLAM — WildGS-SLAM: Monocular Gaussian Splatting SLAM in Dynamic Environments (CVPR 2025) · better on 3 of 3 shared results
- MonST3R — MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion (ICLR 2025) · better on 3 of 3 shared results
- DROID-SLAM — DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras (NeurIPS 2021) · better on 3 of 3 shared results
- MegaSaM — MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos (CVPR 2025) · 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
- ProDyG: Progressive Dynamic Scene Reconstruction via Gaussian Splatting from Monocular Videos (NeurIPS 2025 · similarity 0.89)
- DG-SLAM: Robust Dynamic Gaussian Splatting SLAM with Hybrid Pose Optimization (NeurIPS 2024 · similarity 0.88)
- MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos (CVPR 2025 · similarity 0.88)
- WildGS-SLAM: Monocular Gaussian Splatting SLAM in Dynamic Environments (CVPR 2025 · similarity 0.88)
- MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors (CVPR 2025 · similarity 0.88)
- Photo-SLAM: Real-time Simultaneous Localization and Photorealistic Mapping for Monocular Stereo and RGB-D Cameras (CVPR 2024 · 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.
