Research map / 3D vision / Depth and stereo
GO-SLAM: Global Optimization for Consistent 3D Instant Reconstruction
Youmin Zhang, Fabio Tosi, Stefano Mattoccia, Matteo Poggi
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 top-ranked keyframe selection (largest pose change) on top of latest and stratified keyframes (ablation) | GO-SLAM · Replica | avg F-score: 83.13 -> 85.56 | Improved |
| add stratified sampling to latest-only keyframe selection (ablation) | GO-SLAM · Replica | avg F-score: 49.55 -> 83.13 | Improved |
| add depth loss to RGB loss (ablation) | GO-SLAM · Replica | avg F-score: 34.64 -> 83.50 | Improved |
| add SDF loss and Eikonal loss to color and depth losses (ablation) | GO-SLAM · Replica | avg F-score: 83.50 -> 85.56 | Improved |
| add loop closing to the DROID-SLAM VO baseline (ablation) | GO-SLAM · ScanNet RGB-D | avg ATE RMSE (cm): 11.59 -> 8.83 | Improved |
| add online full bundle adjustment (ablation) | GO-SLAM · ScanNet RGB-D | avg ATE RMSE (cm): 11.59 -> 7.11 | Improved |
| combine loop closing with full BA (ablation) | GO-SLAM · ScanNet RGB-D | avg ATE RMSE (cm): 7.11 -> 7.02 | Improved |
| skip 7/8 of RGB-D frames for 8x speedup (ablation) | GO-SLAM · ScanNet / Replica | avg ATE RMSE (cm): 7.02 -> 7.28 | No clear effect |
| use GO-SLAM instead of DROID-SLAM with offline global BA on long monocular sequences | GO-SLAM · ScanNet monocular | avg ATE RMSE (cm): 52.60 -> 17.59 | Improved |
| use GO-SLAM instead of DROID-SLAM on EuRoC stereo | GO-SLAM · EuRoC stereo | avg ATE RMSE (m): 0.024 vs 0.024 | No clear effect |
Later papers that compared with this method
8 later accepted papers report GO-SLAM as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.
- UniMapping: Unified SLAM Framework for Map-Centric Embodied Perception (ICML 2026 · better on 0 of 1 shared result)
- VarSplat: Uncertainty-aware 3D Gaussian Splatting for Robust RGB-D SLAM (CVPR 2026 · better on 1 of 1 shared result)
- Online3R: Online Learning for Consistent Sequential Reconstruction Based on Geometry Foundation Model (CVPR 2026 · better on 1 of 1 shared result)
- FoundationSLAM: Unleashing the Power of Depth Foundation Models for End-to-End Dense Visual SLAM (AAAI 2026 · better on 1 of 1 shared result)
- MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors (CVPR 2025 · better on 1 of 1 shared result)
- MambaVO: Deep Visual Odometry Based on Sequential Matching Refinement and Training Smoothing (CVPR 2025 · better on 1 of 1 shared result)
- Loopy-SLAM: Dense Neural SLAM with Loop Closures (CVPR 2024 · better on 1 of 3 shared results)
- Photo-SLAM: Real-time Simultaneous Localization and Photorealistic Mapping for Monocular Stereo and RGB-D Cameras (CVPR 2024 · better on 1 of 2 shared results)
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 6 of 7 shared results
- NICE-SLAM — NICE-SLAM: Neural Implicit Scalable Encoding for SLAM (CVPR 2022) · better on 3 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
- SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videos (CVPR 2025 · similarity 0.90)
- MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors (CVPR 2025 · similarity 0.89)
- Loopy-SLAM: Dense Neural SLAM with Loop Closures (CVPR 2024 · similarity 0.89)
- DG-SLAM: Robust Dynamic Gaussian Splatting SLAM with Hybrid Pose Optimization (NeurIPS 2024 · similarity 0.89)
- GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting (CVPR 2024 · similarity 0.89)
- Photo-SLAM: Real-time Simultaneous Localization and Photorealistic Mapping for Monocular Stereo and RGB-D Cameras (CVPR 2024 · 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.
