Research map / 3D vision / Depth and stereo
DROID-SLAM in the Wild
Moyang Li, Zihan Zhu, Marc Pollefeys, Daniel Barath
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 uncertainty-aware bundle adjustment (ablation) | DROID-W · Bonn RGB-D Dynamic | ATE RMSE (cm): 5.13 -> 2.30 | Improved |
| add monocular depth (Metric3D) regularization (ablation) | DROID-W · Bonn RGB-D Dynamic | ATE RMSE (cm): 3.30 -> 2.30 | Improved |
| decouple bidirectional uncertainties in similarity loss (ablation) | DROID-W · Bonn RGB-D Dynamic | ATE RMSE (cm): 2.57 -> 2.30 | Improved |
| add local affine mapping for uncertainty (ablation) | DROID-W · Bonn RGB-D Dynamic | ATE RMSE (cm): 2.47 -> 2.30 | Improved |
| add weight decay on affine mapping (ablation) | DROID-W · Bonn RGB-D Dynamic | ATE RMSE (cm): 2.34 -> 2.30 | Improved |
| add feature-similarity uncertainty to DROID-SLAM | DROID-SLAM · Bonn RGB-D Dynamic | ATE RMSE (cm): 4.91 -> 2.30 | Improved |
| add feature-similarity uncertainty to DROID-SLAM | DROID-SLAM · TUM RGB-D | ATE RMSE (cm): 1.62 -> 1.36 | Improved |
| add feature-similarity uncertainty to DROID-SLAM | DROID-SLAM · DROID-W dataset | ATE RMSE (m): 1.460 -> 0.230 | Improved |
| use DROID-W instead of DROID-SLAM | DROID-SLAM · DyCheck haru | ATE RMSE: 0.005 -> 0.093 | Hurt |
| use DROID-W instead of WildGS-SLAM | WildGS-SLAM · runtime | FPS: 0.22 -> 10.57 | Improved |
| use DROID-W instead of DROID-SLAM | DROID-SLAM · runtime | FPS: 19.89 -> 10.57 | Hurt |
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 5 of 5 shared results
- DROID-SLAM — DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras (NeurIPS 2021) · better on 4 of 5 shared results
- TTT3R — TTT3R: 3D Reconstruction as Test-Time Training (ICLR 2026) · 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
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
- WildGS-SLAM: Monocular Gaussian Splatting SLAM in Dynamic Environments (CVPR 2025 · similarity 0.91)
- DG-SLAM: Robust Dynamic Gaussian Splatting SLAM with Hybrid Pose Optimization (NeurIPS 2024 · similarity 0.88)
- ProDyG: Progressive Dynamic Scene Reconstruction via Gaussian Splatting from Monocular Videos (NeurIPS 2025 · similarity 0.87)
- Photo-SLAM: Real-time Simultaneous Localization and Photorealistic Mapping for Monocular Stereo and RGB-D Cameras (CVPR 2024 · similarity 0.86)
- CTO-SLAM: Contour Tracking for Object-Level Robust 4D SLAM (AAAI 2024 · similarity 0.86)
- 4DTAM: Non-Rigid Tracking and Mapping via Dynamic Surface Gaussians (CVPR 2025 · similarity 0.86)
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.
