# S-BEVLoc: BEV-based Self-supervised Framework for Large-scale LiDAR Global Localization

arXiv: https://arxiv.org/abs/2509.09110 · HTML: https://mlsanity.com/paper/2509.09110/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 33 references that are in the map.
- First posted on arXiv 11 Sep 2025.

## Builds on (most cited first, 20 of 20)

- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [Training Region-based Object Detectors with Online Hard Example Mining](https://mlsanity.com/paper/1604.03540/) (2016)
- [PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognition](https://mlsanity.com/paper/1804.03492/) (2018)
- [OverlapTransformer: An Efficient and Rotation-Invariant Transformer Network for LiDAR-Based Place Recognition](https://mlsanity.com/paper/2203.03397/) (2022)
- [ALSO: Automotive Lidar Self-supervision by Occupancy estimation](https://mlsanity.com/paper/2212.05867/) (2022)
- [LCDNet: Deep Loop Closure Detection and Point Cloud Registration for LiDAR SLAM](https://mlsanity.com/paper/2103.05056/) (2021)
- [LoGG3D-Net: Locally Guided Global Descriptor Learning for 3D Place Recognition](https://mlsanity.com/paper/2109.08336/) (2021)
- [A Survey on Global LiDAR Localization: Challenges, Advances and Open Problems](https://mlsanity.com/paper/2302.07433/) (2023)
- [BEVPlace: Learning LiDAR-based Place Recognition using Bird's Eye View Images](https://mlsanity.com/paper/2302.14325/) (2023)
- [BVMatch: Lidar-based Place Recognition Using Bird's-eye View Images](https://mlsanity.com/paper/2109.00317/) (2021)
- [EgoNN: Egocentric Neural Network for Point Cloud Based 6DoF Relocalization at the City Scale](https://mlsanity.com/paper/2110.12486/) (2021)
- [BEVContrast: Self-Supervision in BEV Space for Automotive Lidar Point Clouds](https://mlsanity.com/paper/2310.17281/) (2023)
- [LiDAR-Based Place Recognition For Autonomous Driving: A Survey](https://mlsanity.com/paper/2306.10561/) (2023)
- [CVTNet: A Cross-View Transformer Network for Place Recognition Using LiDAR Data](https://mlsanity.com/paper/2302.01665/) (2023)
- [Directional Statistics-based Deep Metric Learning for Image Classification and Retrieval](https://mlsanity.com/paper/1802.09662/) (2018)
- [Fast and Accurate Deep Loop Closing and Relocalization for Reliable LiDAR SLAM](https://mlsanity.com/paper/2309.08086/) (2023)
- [BoW3D: Bag of Words for Real-Time Loop Closing in 3D LiDAR SLAM](https://mlsanity.com/paper/2208.07473/) (2022)
- [3D-BBS: Global Localization for 3D Point Cloud Scan Matching Using Branch-and-Bound Algorithm](https://mlsanity.com/paper/2310.10023/) (2023)
- [Narrowing your FOV with SOLiD: Spatially Organized and Lightweight Global Descriptor for FOV-constrained LiDAR Place Recognition](https://mlsanity.com/paper/2408.07330/) (2024)
- [LinK3D: Linear Keypoints Representation for 3D LiDAR Point Cloud](https://mlsanity.com/paper/2206.05927/) (2022)

## Abstract (arXiv)

LiDAR-based global localization is an essential component of simultaneous localization and mapping (SLAM), which helps loop closure and re-localization. Current approaches rely on ground-truth poses obtained from GPS or SLAM odometry to supervise network training. Despite the great success of these supervised approaches, substantial cost and effort are required for high-precision ground-truth pose acquisition. In this work, we propose S-BEVLoc, a novel self-supervised framework based on bird's-eye view (BEV) for LiDAR global localization, which eliminates the need for ground-truth poses and is highly scalable. We construct training triplets from single BEV images by leveraging the known geographic distances between keypoint-centered BEV patches. Convolutional neural network (CNN) is used to extract local features, and NetVLAD is employed to aggregate global descriptors. Moreover, we introduce SoftCos loss to enhance learning from the generated triplets. Experimental results on the large-scale KITTI and NCLT datasets show that S-BEVLoc achieves state-of-the-art performance in place recognition, loop closure, and global localization tasks, while offering scalability that would require extra effort for supervised approaches.