Research map / 3D vision / Human pose estimation
SGLoc: Scene Geometry Encoding for Outdoor LiDAR Localization
Wen Li, Shangshu Yu, Cheng Wang, Guosheng Hu, Siqi Shen, Chenglu Wen
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 |
|---|---|---|---|
| Decouple pose prediction into point-cloud correspondence regression and RANSAC pose estimation | LiDAR localization on Oxford and NCLT · Oxford | position error (m): 8.62m -> 3.14m | Improved |
| Use Pose Quality Evaluation and Enhancement to correct training and evaluation poses | SGLoc · Oxford | position error (m): 3.14m -> 1.53m | Improved |
| Add the IGCC loss (ablation) | SGLoc · Oxford w/o PQEE | position error (m): 3.95m -> 3.46m | Improved |
| Add the IGCC loss (ablation) | SGLoc · NCLT | position error (m): 2.73m -> 2.62m | Improved |
| Add the TSFA module (ablation) | SGLoc · Oxford w/o PQEE | position error (m): 3.95m -> 3.23m | Improved |
| Add the TSFA module (ablation) | SGLoc · NCLT | position error (m): 2.73m -> 1.98m | Improved |
| Add PGO post-processing (ablation) | SGLoc · Quality-enhanced Oxford | position error (m): 1.79m -> 1.58m; 1.81m -> 1.56m; 1.33m -> 1.10m; 1.19m -> 0.99m | Improved |
| Add PGO post-processing (ablation) | SGLoc · NCLT | position error (m): 1.20m -> 0.88m; 1.20m -> 0.85m; 1.12m -> 0.79m; 3.81m -> 3.25m | Improved |
| Add both IGCC and TSFA (ablation) | SGLoc · NCLT | orientation error (°): 3.51◦ -> 3.54◦ | Hurt |
Later papers that compared with this method
3 later accepted papers report SGLoc as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.
- SOAR: Regression-based LiDAR Relocalization for UAVs (NeurIPS 2026 · better on 2 of 2 shared results)
- LEADER: Learning Reliable Local-to-Global Correspondences for LiDAR Relocalization (CVPR 2026 · better on 1 of 1 shared result)
- DiffLoc: Diffusion Model for Outdoor LiDAR Localization (CVPR 2024 · 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
- LightLoc: Learning Outdoor LiDAR Localization at Light Speed (CVPR 2025 · similarity 0.90)
- DiffLoc: Diffusion Model for Outdoor LiDAR Localization (CVPR 2024 · similarity 0.90)
- SOAR: Regression-based LiDAR Relocalization for UAVs (NeurIPS 2026 · similarity 0.87)
- GBlobs: Explicit Local Structure via Gaussian Blobs for Improved Cross-Domain LiDAR-based 3D Object Detection (CVPR 2025 · similarity 0.86)
- LiSA: LiDAR Localization with Semantic Awareness (CVPR 2024 · similarity 0.85)
- GeoNLF: Geometry guided Pose-Free Neural LiDAR Fields (NeurIPS 2024 · similarity 0.85)
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.
