Research map / 3D vision / Depth and stereo
LRSLAM: Low-rank Representation of Signed Distance Fields in Dense Visual SLAM System
Hongbeen Park, Minjeong Park, Giljoo Nam, Jinkyu Kim
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 |
|---|---|---|---|
| replace tri-plane representation with CP geometry plus Six-axis appearance decomposition | ESLAM · Replica/ScanNet/TUM efficiency | total parameters: 87.3%-90.1% fewer parameters than ESLAM | Improved |
| replace tri-plane representation with low-rank hybrid decomposition | ESLAM · TUM RGB-D fr1/desk | frame processing time (s): 4.56 -> 1.22 | Improved |
| replace tri-plane representation with low-rank hybrid decomposition | ESLAM · ScanNet (6 scenes, average) | ATE Mean (cm): 6.5 -> 6.1 | Improved |
| replace tri-plane representation with low-rank hybrid decomposition on clean synthetic data | ESLAM · Replica room0 (clean depth) | Depth L1 (cm): 1.18 -> 1.58 | Hurt |
| replace tri-plane representation with low-rank hybrid decomposition under noisy depth input | ESLAM · Replica room0 (noisy depth) | Depth L1 (cm): 3.22 -> 1.20 | Improved |
| replace tri-plane representation with low-rank hybrid decomposition on TUM fr3/office | ESLAM · TUM RGB-D fr3/office | ATE RMSE (cm): 2.42 -> 2.79 | Hurt |
| use CP decomposition for geometry and Six-axis decomposition for appearance rather than CP for both (ablation) | LRSLAM · ScanNet ablation | ATE RMSE | Improved |
| use CP or Six-axis decomposition instead of tri-plane (ablation) | scene representation · ScanNet ablation | parameter count: 4%-6% and 8%-12% fewer parameters than tri-plane | Improved |
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.
- ESLAM — ESLAM: Efficient Dense SLAM System Based on Hybrid Representation of Signed Distance Fields (CVPR 2023) · better on 12 of 15 shared results
- NICE-SLAM — NICE-SLAM: Neural Implicit Scalable Encoding for SLAM (CVPR 2022) · 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
- PLGSLAM: Progressive Neural Scene Represenation with Local to Global Bundle Adjustment (CVPR 2024 · similarity 0.89)
- Benchmarking Implicit Neural Representation and Geometric Rendering in Real-Time RGB-D SLAM (CVPR 2024 · similarity 0.89)
- Photo-SLAM: Real-time Simultaneous Localization and Photorealistic Mapping for Monocular Stereo and RGB-D Cameras (CVPR 2024 · similarity 0.87)
- VTGaussian-SLAM: RGBD SLAM for Large Scale Scenes with Splatting View-Tied 3D Gaussians (ICML 2025 · similarity 0.86)
- Loopy-SLAM: Dense Neural SLAM with Loop Closures (CVPR 2024 · similarity 0.86)
- VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold (NeurIPS 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.
