Research map / 3D vision / Depth and stereo
UniSim-SLAM: Feed-Forward SLAM with Unified Sim(3) Optimization
inha Lee, Dongjae Jeong, Junhee Lee, Kyungdon Joo
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 the multi-view backend over tracking only (overlap 2) (ablation) | UniSim-SLAM · 7-Scenes (avg) | ATE RMSE (m): 0.124 -> 0.020 | Improved |
| add view-to-submap bridge edges (ablation) | UniSim-SLAM · 7-Scenes (avg, overlap 2) | ATE RMSE (m): 0.063 -> 0.020 | Improved |
| add loop closure (ablation) | UniSim-SLAM · 7-Scenes (avg, overlap 2) | ATE RMSE (m): 0.037 -> 0.020 | Improved |
| add submap pose tie constraint (ablation) | UniSim-SLAM · 7-Scenes (avg, overlap 2) | ATE RMSE (m): 0.027 -> 0.020 | Improved |
| add submap scale consistency constraint (ablation) | UniSim-SLAM · 7-Scenes (avg, overlap 2) | ATE RMSE (m): 0.031 -> 0.020 | Improved |
| add submap-to-submap edges (ablation) | UniSim-SLAM · 7-Scenes (avg, overlap 2) | ATE RMSE (m): 0.030 -> 0.020 | Improved |
| add scale anchoring constraint (ablation) | UniSim-SLAM · 7-Scenes (avg, overlap 2) | ATE RMSE (m): 0.020 -> 0.020 | No clear effect |
| add temporal view-to-view edge (non-overlap, phi=0) (ablation) | UniSim-SLAM · 7-Scenes (avg, non-overlap) | ATE RMSE (m): 0.101 -> 0.032 | Improved |
| add temporal view-to-view edge (overlap 2) (ablation) | UniSim-SLAM · 7-Scenes (avg, overlap 2) | ATE RMSE (m): 0.021 -> 0.020 | No clear effect |
| use overlap of 2 frames instead of none (ablation) | UniSim-SLAM · 7-Scenes (avg) | ATE RMSE (m): 0.032 -> 0.020 | Improved |
| raise scale constraint weights from 1 to 50 (ablation) | UniSim-SLAM · 7-Scenes (avg) | ATE RMSE (m): 0.025 -> 0.020 | Improved |
| raise tie constraint weight from 0.2 to 2.0 (ablation) | UniSim-SLAM · 7-Scenes (avg) | ATE RMSE (m): 0.020 -> 0.022 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- SLAM3R — SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB 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
- Revisiting Monocular SLAM with Spatio-Temporal Scene Modeling (CVPR 2026 · similarity 0.90)
- VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold (NeurIPS 2025 · similarity 0.89)
- VTGaussian-SLAM: RGBD SLAM for Large Scale Scenes with Splatting View-Tied 3D Gaussians (ICML 2025 · similarity 0.88)
- DG-SLAM: Robust Dynamic Gaussian Splatting SLAM with Hybrid Pose Optimization (NeurIPS 2024 · similarity 0.87)
- Loopy-SLAM: Dense Neural SLAM with Loop Closures (CVPR 2024 · similarity 0.87)
- GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting (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.
