Research map / 3D vision / Depth and stereo
FoundationSLAM: Unleashing the Power of Depth Foundation Models for End-to-End Dense Visual SLAM
Yuchen Wu, Jiahe Li, Fabio Tosi, Matteo Poggi, Jin Zheng, Xiao Bai
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 Bi-Consistent BA layer plus node- and edge-wise reliability-aware refinement (ablation) | FoundationSLAM · EuRoC | Chamfer distance (m): 0.061 -> 0.048 | Improved |
| add Bi-Consistent BA plus reliability modules (ablation) | FoundationSLAM · EuRoC | ATE (m): 0.021 -> 0.019 | Improved |
| add Bi-Consistent BA plus reliability modules (ablation) | FoundationSLAM · EuRoC | reconstruction accuracy (m): 0.051 -> 0.035 | Improved |
| add either node-wise or edge-wise reliability alone (rows of Table 6 with one component) (ablation) | FoundationSLAM · EuRoC | Chamfer distance (m): 0.061 -> 0.057 / 0.058 | Improved |
| use FoundationSLAM versus MASt3R-SLAM on 7Scenes ATE | FoundationSLAM · 7Scenes seq-01 | ATE: 0.047 -> 0.043 | Improved |
| use FoundationSLAM versus DROID-SLAM on EuRoC mapping | FoundationSLAM · EuRoC VICON room | Chamfer distance (m): 0.065 -> 0.048 | Improved |
| use FoundationSLAM versus DROID-SLAM for speed | FoundationSLAM · EuRoC | FPS: 24 -> 18 | Hurt |
| use FoundationSLAM versus MASt3R-SLAM on TUM-RGBD fr1/360 sequence | FoundationSLAM · TUM-RGBD 360 | ATE RMSE (m): 0.049 -> 0.055 | Hurt |
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.
- DROID-SLAM — DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras (NeurIPS 2021) · better on 5 of 6 shared results
- GO-SLAM — GO-SLAM: Global Optimization for Consistent 3D Instant Reconstruction (ICCV 2023) · better on 1 of 1 shared result
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
- CodeSLAM — Learning a Compact, Optimisable Representation for Dense Visual SLAM (CVPR 2018 · similarity 0.89)
- GO-SLAM: Global Optimization for Consistent 3D Instant Reconstruction (ICCV 2023 · similarity 0.88)
- MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors (CVPR 2025 · similarity 0.86)
- Depth2Pose: A Pose-Based Benchmark for Monocular Depth Estimation without Ground-Truth Depth (NeurIPS 2026 · similarity 0.86)
- Distilling Monocular Foundation Model for Fine-grained Depth Completion (CVPR 2025 · similarity 0.86)
- Flow-NeRF: Joint Learning of Geometry, Poses, and Dense Flow within Unified Neural Representations (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.
