Research map / 3D vision / Depth and stereo
BEV-SLD: Self-Supervised Scene Landmark Detection for Global Localization with LiDAR Bird's-Eye View Images
David Skuddis, Vincent Ress, Wei Zhang, Vincent Ofosu Nyako, Norbert Haala
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 |
|---|---|---|---|
| jointly optimize landmark positions instead of freezing them (ablation) | BEV-SLD · MCD ntu day 10 | success rate: 40.35 -> 92.04 | Improved |
| jointly optimize landmark positions instead of freezing them (ablation) | BEV-SLD · MCD ntu day 02 | success rate: 68.05 -> 100.00 | Improved |
| jointly optimize landmark positions instead of freezing them (ablation) | BEV-SLD · MCD ntu day 10 | median translational error: 2.43 -> 0.20 | Improved |
| jointly optimize landmark positions instead of freezing them (ablation) | BEV-SLD · MCD ntu night 04 | success rate: 38.65 -> 91.82 | Improved |
| BEV-SLD versus BEVPlace++ (K) on MCD | BEV-SLD · MCD ntu day 10 | success rate: 81.53 -> 92.04 | Improved |
| BEV-SLD versus BEVPlace++ (S) on Wild-Places forest | BEV-SLD · Wild-Places V-02 | success rate: 42.45 -> 63.96 | Improved |
| BEV-SLD versus BEVPlace++ (S) on NCLT 05-11 | BEV-SLD · NCLT 2012-05-11 | success rate: 82.27 -> 82.10 | No clear effect |
| BEV-SLD versus LightLoc on Factory Floor | BEV-SLD · Factory Floor | success rate: 93.61 -> 92.92 | Hurt |
| scale landmarks from 614 to 100k | BEV-SLD · network runtime | runtime (ms): 17.3 -> 17.8 | No clear effect |
| scale landmarks from 614 to 100k | BEV-SLD · memory footprint | memory (MB): 20 -> 173.7 | 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.
- LightLoc — LightLoc: Learning Outdoor LiDAR Localization at Light Speed (CVPR 2025) · better on 5 of 6 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
- PC-BEV: An Efficient Polar-Cartesian BEV Fusion Framework for LiDAR Semantic Segmentation (AAAI 2025 · similarity 0.86)
- ForestLPR: LiDAR Place Recognition in Forests Attentioning Multiple BEV Density Images (CVPR 2025 · similarity 0.86)
- GeoBEV: Learning Geometric BEV Representation for Multi-view 3D Object Detection (AAAI 2025 · similarity 0.86)
- Map It Anywhere: Empowering BEV Map Prediction using Large-scale Public Datasets (NeurIPS 2024 · similarity 0.85)
- L2RSI: Cross-view LiDAR-based Place Recognition for Large-scale Urban Scenes via Remote Sensing Imagery (NeurIPS 2025 · similarity 0.85)
- BEV-MAE: Bird’s Eye View Masked Autoencoders for Point Cloud Pre-training in Autonomous Driving Scenarios (AAAI 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.
