# BEVDiffLoc: End-to-End LiDAR Global Localization in BEV View based on Diffusion Model

arXiv: https://arxiv.org/abs/2503.11372 · HTML: https://mlsanity.com/paper/2503.11372/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 34 references that are in the map.
- First posted on arXiv 14 Mar 2025.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Early Convolutions Help Transformers See Better](https://mlsanity.com/paper/2106.14881/) (2021)
- [PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognition](https://mlsanity.com/paper/1804.03492/) (2018)
- [Visual Camera Re-Localization from RGB and RGB-D Images Using DSAC](https://mlsanity.com/paper/2002.12324/) (2020)
- [Learning Less is More - 6D Camera Localization via 3D Surface Regression](https://mlsanity.com/paper/1711.10228/) (2017)
- [The Oxford Radar RobotCar Dataset: A Radar Extension to the Oxford RobotCar Dataset](https://mlsanity.com/paper/1909.01300/) (2019)
- [RangeViT: Towards Vision Transformers for 3D Semantic Segmentation in Autonomous Driving](https://mlsanity.com/paper/2301.10222/) (2023)
- [OverlapNet: Loop Closing for LiDAR-based SLAM](https://mlsanity.com/paper/2105.11344/) (2021)
- [Scan Context++: Structural Place Recognition Robust to Rotation and Lateral Variations in Urban Environments](https://mlsanity.com/paper/2109.13494/) (2021)
- [Map-Relative Pose Regression for Visual Re-Localization](https://mlsanity.com/paper/2404.09884/) (2024)
- [Real-Time RGB-D Camera Pose Estimation in Novel Scenes using a Relocalisation Cascade](https://mlsanity.com/paper/1810.12163/) (2018)
- [PointLoc: Deep Pose Regressor for LiDAR Point Cloud Localization](https://mlsanity.com/paper/2003.02392/) (2020)
- [Range Image-based LiDAR Localization for Autonomous Vehicles](https://mlsanity.com/paper/2105.12121/) (2021)
- [BVMatch: Lidar-based Place Recognition Using Bird's-eye View Images](https://mlsanity.com/paper/2109.00317/) (2021)
- [HypLiLoc: Towards Effective LiDAR Pose Regression with Hyperbolic Fusion](https://mlsanity.com/paper/2304.00932/) (2023)
- [Fast and Accurate Deep Loop Closing and Relocalization for Reliable LiDAR SLAM](https://mlsanity.com/paper/2309.08086/) (2023)
- [SALSA: Swift Adaptive Lightweight Self-Attention for Enhanced LiDAR Place Recognition](https://mlsanity.com/paper/2407.08260/) (2024)
- [RING#: PR-by-PE Global Localization with Roto-translation Equivariant Gram Learning](https://mlsanity.com/paper/2409.00206/) (2024)
- [FlashMix: Fast Map-Free LiDAR Localization via Feature Mixing and Contrastive-Constrained Accelerated Training](https://mlsanity.com/paper/2410.00702/) (2024)

## Built on by (most cited first, 2 of 2)

- [LightLoc++: Sensor-Robust Representation Learning for Efficient Outdoor LiDAR Localization](https://mlsanity.com/paper/2608.15317/) (2026)
- [ReLoc: Rethinking Scene Coordinate Regression Architecture for Robust Outdoor LiDAR-based Localization](https://mlsanity.com/paper/2609.33344/) (2026)

## Abstract (arXiv)

Localization is one of the core parts of modern robotics. Classic localization methods typically follow the retrieve-then-register paradigm, achieving remarkable success. Recently, the emergence of end-to-end localization approaches has offered distinct advantages, including a streamlined system architecture and the elimination of the need to store extensive map data. Although these methods have demonstrated promising results, current end-to-end localization approaches still face limitations in robustness and accuracy. Bird's-Eye-View (BEV) image is one of the most widely adopted data representations in autonomous driving. It significantly reduces data complexity while preserving spatial structure and scale consistency, making it an ideal representation for localization tasks. However, research on BEV-based end-to-end localization remains notably insufficient. To fill this gap, we propose BEVDiffLoc, a novel framework that formulates LiDAR localization as a conditional generation of poses. Leveraging the properties of BEV, we first introduce a specific data augmentation method to significantly enhance the diversity of input data. Then, the Maximum Feature Aggregation Module and Vision Transformer are employed to learn robust features while maintaining robustness against significant rotational view variations. Finally, we incorporate a diffusion model that iteratively refines the learned features to recover the absolute pose. Extensive experiments on the Oxford Radar RobotCar and NCLT datasets demonstrate that BEVDiffLoc outperforms the baseline methods. Our code is available at https://github.com/nubot-nudt/BEVDiffLoc.