mlsanityData to 7 Oct 2026

BEV-SLD: Self-Supervised Scene Landmark Detection for Global Localization with LiDAR Bird's-Eye View Images

arXiv 2603.17159 ↗First posted 17 Mar 2026cs.CV cs.ROcited by 1

Not on the map. Why?

Abstract (arXiv)

We present BEV-SLD, a LiDAR global localization method building on the Scene Landmark Detection (SLD) concept. Unlike scene-agnostic pipelines, our self-supervised approach leverages bird's-eye-view (BEV) images to discover scene-specific patterns at a prescribed spatial density and treat them as landmarks. A consistency loss aligns learnable global landmark coordinates with per-frame heatmaps, yielding consistent landmark detections across the scene. Across campus, industrial, and forest environments, BEV-SLD delivers robust localization and achieves strong performance compared to state-of-the-art methods.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 21 of its 40 references that are in the map. First posted on arXiv 17 Mar 2026.

Builds on

21 of 40 references.

References · 21

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2018PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognitioncited by 197
  4. 2020MinkLoc3D: Point Cloud Based Large-Scale Place Recognitioncited by 114
  5. 2021OverlapNet: Loop Closing for LiDAR-based SLAMcited by 72
  6. 2021Scan Context++: Structural Place Recognition Robust to Rotation and Lateral Variations in Urban Environmentscited by 72
  7. 2022OverlapTransformer: An Efficient and Rotation-Invariant Transformer Network for LiDAR-Based Place Recognitioncited by 69
  8. 2021LCDNet: Deep Loop Closure Detection and Point Cloud Registration for LiDAR SLAMcited by 67
  9. 2021LoGG3D-Net: Locally Guided Global Descriptor Learning for 3D Place Recognitioncited by 51
  10. 2020Locus: LiDAR-based Place Recognition using Spatiotemporal Higher-Order Poolingcited by 38
  11. 2021CT-ICP: Real-time Elastic LiDAR Odometry with Loop Closurecited by 38
  12. 2021EgoNN: Egocentric Neural Network for Point Cloud Based 6DoF Relocalization at the City Scalecited by 25
9 more
  1. 2018Feature Pyramid Network for Multi-Class Land Segmentationcited by 24
  2. 2023HypLiLoc: Towards Effective LiDAR Pose Regression with Hyperbolic Fusioncited by 24
  3. 2024KISS-Matcher: Fast and Robust Point Cloud Registration Revisitedcited by 16
  4. 2023Fast and Accurate Deep Loop Closing and Relocalization for Reliable LiDAR SLAMcited by 15
  5. 2024MCD: Diverse Large-Scale Multi-Campus Dataset for Robot Perceptioncited by 15
  6. 2025LightLoc: Learning Outdoor LiDAR Localization at Light Speedcited by 10
  7. 20233D-BBS: Global Localization for 3D Point Cloud Scan Matching Using Branch-and-Bound Algorithmcited by 8
  8. 2024Improved Scene Landmark Detection for Camera Localizationcited by 4
  9. 2024DMSA -- Dense Multi Scan Adjustment for LiDAR Inertial Odometry and Global Optimizationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Aerial-ground LiDAR place recognition with patch-level self-supervised learning and expanded reciprocal re-rankingcited by 0