Research map / 3D vision / Depth and stereo
Elaborate Monocular Point and Line SLAM With Robust Initialization
Sang Jun Lee, Sung Soo Hwang
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 |
|---|---|---|---|
| use rank-1 factorization initialization instead of conventional ORB-SLAM initialization | ORB-SLAM point SLAM · TUM RGB-D f1_xyz | ATE RMSE (cm): 1.2514 -> 1.0178 | Improved |
| use proposed initialization instead of conventional | ORB-SLAM point SLAM · TUM RGB-D f2_xyz | ATE RMSE (cm): 0.3655 -> 0.3062 | Improved |
| use proposed initialization instead of conventional | ORB-SLAM point SLAM · TUM RGB-D f2_desk | RPE (cm): 7.2342 -> 6.7241 | Improved |
| use proposed initialization instead of conventional | ORB-SLAM point SLAM · TUM RGB-D f3_sit_static | ATE RMSE (cm): 0.3783 -> 0.5934 | Hurt |
| use proposed initialization instead of conventional | ORB-SLAM point SLAM · TUM RGB-D f1_floor | ATE RMSE (cm): 3.4003 -> 3.4938 | No clear effect |
| use proposed initialization where conventional fails | ORB-SLAM point SLAM · TUM RGB-D f3_nstr_tex_far | ATE RMSE (cm): ambiguity -> 3.6836 | Improved |
| use Plucker line representation (RIPPL-SLAM) instead of endpoints (EPL-SLAM) | point-line SLAM · TUM RGB-D f1_xyz | ATE RMSE (cm): 1.1873 -> 0.9399 | Improved |
| use RIPPL-SLAM instead of PPL-SLAM | point-line SLAM · TUM RGB-D f1_floor | ATE RMSE (cm): 4.7881 -> 3.4988 | Improved |
| use RIPPL-SLAM instead of EPL-SLAM | point-line SLAM · TUM RGB-D f2_desk | ATE RMSE (cm): 5.3653 -> 5.5371 | Hurt |
| use RIPPL-SLAM instead of PPL-SLAM | point-line SLAM · TUM RGB-D f2_xyz | ATE RMSE (cm): 0.3436 -> 0.3907 | Hurt |
| use RIPPL-SLAM instead of EPL-SLAM | point-line SLAM · TUM RGB-D f3_nstr_tex_far | ATE RMSE (cm): ambiguity -> 1.5060 | Improved |
| optimize 4-parameter orthonormal line instead of 6-parameter endpoints | local BA · speed | local BA time: about 1.5 times faster | Improved |
Closest papers by meaning
- Revisiting Monocular SLAM with Spatio-Temporal Scene Modeling (CVPR 2026 · similarity 0.87)
- Robust and Efficient Monocular 3D Gaussian SLAM for Kilometer-Scale Outdoor Scenes (ECCV 2026 · similarity 0.84)
- MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors (CVPR 2025 · similarity 0.84)
- Gaussian Splatting SLAM (CVPR 2024 · similarity 0.83)
- Fully Geometric Panoramic Localization (CVPR 2024 · similarity 0.82)
- DG-SLAM: Robust Dynamic Gaussian Splatting SLAM with Hybrid Pose Optimization (NeurIPS 2024 · similarity 0.82)
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.
