# BEVPlace++: Fast, Robust, and Lightweight LiDAR Global Localization for Unmanned Ground Vehicles

arXiv: https://arxiv.org/abs/2408.01841 · HTML: https://mlsanity.com/paper/2408.01841/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Aug 2024.

## Built on by (most cited first, 19 of 19)

- [VPGS-SLAM: Voxel-based Progressive 3D Gaussian SLAM in Large-Scale Scenes](https://mlsanity.com/paper/2505.18992/) (2025)
- [VGGT-MPR: VGGT-Enhanced Multimodal Place Recognition in Autonomous Driving Environments](https://mlsanity.com/paper/2602.19735/) (2026)
- [VLM-Loc: Localization in Point Cloud Maps via Vision-Language Models](https://mlsanity.com/paper/2603.09826/) (2026)
- [Environment-Driven Online LiDAR-Camera Extrinsic Calibration](https://mlsanity.com/paper/2502.00801/) (2025)
- [LRFusionPR: A Polar BEV-Based LiDAR-Radar Fusion Network for Place Recognition](https://mlsanity.com/paper/2504.19186/) (2025)
- [Polar Perspectives: Evaluating 2-D LiDAR Projections for Robust Place Recognition with Visual Foundation Models](https://mlsanity.com/paper/2512.02897/) (2025)
- [M3DMap: Object-aware Multimodal 3D Mapping for Dynamic Environments](https://mlsanity.com/paper/2508.17044/) (2025)
- [PRISM-Loc: a Lightweight Long-range LiDAR Localization in Urban Environments with Topological Maps](https://mlsanity.com/paper/2506.15849/) (2025)
- [Single-Frame Point-Pixel Registration via Supervised Cross-Modal Feature Matching](https://mlsanity.com/paper/2506.22784/) (2025)
- [Gaussian Semantic Field for One-shot LiDAR Global Localization](https://mlsanity.com/paper/2510.12101/) (2025)
- [TransLocNet: Cross-Modal Attention for Aerial-Ground Vehicle Localization with Contrastive Learning](https://mlsanity.com/paper/2512.10419/) (2025)
- [From Single Scan to Sequential Consistency: A New Paradigm for LIDAR Relocalization](https://mlsanity.com/paper/2602.03198/) (2026)
- [SOAR: Regression-based LiDAR Relocalization for UAVs](https://mlsanity.com/paper/2602.13267/) (2026)
- [RLPR: Radar-to-LiDAR Place Recognition via Two-Stage Asymmetric Cross-Modal Alignment for Autonomous Driving](https://mlsanity.com/paper/2603.07920/) (2026)
- [TOL: Textual Localization with OpenStreetMap](https://mlsanity.com/paper/2604.01644/) (2026)
- [EdgeLPR: On the Deep Neural Network trade-off between Precision and Performance in LiDAR Place Recognition](https://mlsanity.com/paper/2605.02275/) (2026)
- [Learning 1-Bit LiDAR-based Localization with Auxiliary Objective](https://mlsanity.com/paper/2606.27729/) (2026)
- [LightLoc++: Sensor-Robust Representation Learning for Efficient Outdoor LiDAR Localization](https://mlsanity.com/paper/2608.15317/) (2026)
- [RoSe-SLAM: Robust Semantic-Aware Gaussian Splatting SLAM from Dynamic Monocular Videos](https://mlsanity.com/paper/2608.29003/) (2026)

## Abstract (arXiv)

This article introduces BEVPlace++, a novel, fast, and robust LiDAR global localization method for unmanned ground vehicles. It uses lightweight convolutional neural networks (CNNs) on Bird's Eye View (BEV) image-like representations of LiDAR data to achieve accurate global localization through place recognition, followed by 3-DoF pose estimation. Our detailed analyses reveal an interesting fact that CNNs are inherently effective at extracting distinctive features from LiDAR BEV images. Remarkably, keypoints of two BEV images with large translations can be effectively matched using CNN-extracted features. Building on this insight, we design a Rotation Equivariant Module (REM) to obtain distinctive features while enhancing robustness to rotational changes. A Rotation Equivariant and Invariant Network (REIN) is then developed by cascading REM and a descriptor generator, NetVLAD, to sequentially generate rotation equivariant local features and rotation invariant global descriptors. The global descriptors are used first to achieve robust place recognition, and then local features are used for accurate pose estimation. reviseExperimental results on seven public datasets and our UGV platform demonstrate that BEVPlace++, even when trained on a small dataset (3000 frames of KITTI) only with place labels, generalizes well to unseen environments, performs consistently across different days and years, and adapts to various types of LiDAR scanners. BEVPlace++ achieves state-of-the-art performance in multiple tasks, including place recognition, loop closure detection, and global localization. Additionally, BEVPlace++ is lightweight, runs in real-time, and does not require accurate pose supervision, making it highly convenient for deployment. reviseThe source codes are publicly available at https://github.com/zjuluolun/BEVPlace2.