# BEV2PR: BEV-Enhanced Visual Place Recognition with Structural Cues

arXiv: https://arxiv.org/abs/2403.06600 · HTML: https://mlsanity.com/paper/2403.06600/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 31 references that are in the map.
- First posted on arXiv 11 Mar 2024.

## Builds on (most cited first, 24 of 24)

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D](https://mlsanity.com/paper/2008.05711/) (2020)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [Fine-tuning CNN Image Retrieval with No Human Annotation](https://mlsanity.com/paper/1711.02512/) (2017)
- [HDMapNet: An Online HD Map Construction and Evaluation Framework](https://mlsanity.com/paper/2107.06307/) (2021)
- [Rethinking Visual Geo-localization for Large-Scale Applications](https://mlsanity.com/paper/2204.02287/) (2022)
- [MixVPR: Feature Mixing for Visual Place Recognition](https://mlsanity.com/paper/2303.02190/) (2023)
- [EigenPlaces: Training Viewpoint Robust Models for Visual Place Recognition](https://mlsanity.com/paper/2308.10832/) (2023)
- [Self-supervising Fine-grained Region Similarities for Large-scale Image Localization](https://mlsanity.com/paper/2006.03926/) (2020)
- [TransVPR: Transformer-based place recognition with multi-level attention aggregation](https://mlsanity.com/paper/2201.02001/) (2022)
- [GSV-Cities: Toward Appropriate Supervised Visual Place Recognition](https://mlsanity.com/paper/2210.10239/) (2022)
- [Aggregating Deep Convolutional Features for Image Retrieval](https://mlsanity.com/paper/1510.07493/) (2015)
- [MinkLoc++: Lidar and Monocular Image Fusion for Place Recognition](https://mlsanity.com/paper/2104.05327/) (2021)
- [BEVPlace: Learning LiDAR-based Place Recognition using Bird's Eye View Images](https://mlsanity.com/paper/2302.14325/) (2023)
- [AdaFusion: Visual-LiDAR Fusion with Adaptive Weights for Place Recognition](https://mlsanity.com/paper/2111.11739/) (2021)
- [DASGIL: Domain Adaptation for Semantic and Geometric-aware Image-based Localization](https://mlsanity.com/paper/2010.00573/) (2020)
- [MobileSal: Extremely Efficient RGB-D Salient Object Detection](https://mlsanity.com/paper/2012.13095/) (2020)
- [Augmenting Visual Place Recognition with Structural Cues](https://mlsanity.com/paper/2003.00278/) (2020)
- [CORAL: Colored structural representation for bi-modal place recognition](https://mlsanity.com/paper/2011.10934/) (2020)
- [LCPR: A Multi-Scale Attention-Based LiDAR-Camera Fusion Network for Place Recognition](https://mlsanity.com/paper/2311.03198/) (2023)
- [PIC-Net: Point Cloud and Image Collaboration Network for Large-Scale Place Recognition](https://mlsanity.com/paper/2008.00658/) (2020)
- [StructVPR: Distill Structural Knowledge with Weighting Samples for Visual Place Recognition](https://mlsanity.com/paper/2212.00937/) (2022)
- [OneShot Global Localization: Instant LiDAR-Visual Pose Estimation](https://mlsanity.com/paper/2003.13279/) (2020)

## Built on by (most cited first, 3 of 3)

- [Range and Bird's Eye View Fused Cross-Modal Visual Place Recognition](https://mlsanity.com/paper/2502.11742/) (2025)
- [Flexible and Efficient Spatio-Temporal Transformer for Sequential Visual Place Recognition](https://mlsanity.com/paper/2510.04282/) (2025)
- [VVLoc: Prior-free 3-DoF Vehicle Visual Localization](https://mlsanity.com/paper/2602.00810/) (2026)

## Abstract (arXiv)

In this paper, we propose a new image-based visual place recognition (VPR) framework by exploiting the structural cues in bird's-eye view (BEV) from a single monocular camera. The motivation arises from two key observations about place recognition methods based on both appearance and structure: 1) For the methods relying on LiDAR sensors, the integration of LiDAR in robotic systems has led to increased expenses, while the alignment of data between different sensors is also a major challenge. 2) Other image-/camera-based methods, involving integrating RGB images and their derived variants (eg, pseudo depth images, pseudo 3D point clouds), exhibit several limitations, such as the failure to effectively exploit the explicit spatial relationships between different objects. To tackle the above issues, we design a new BEV-enhanced VPR framework, namely BEV2PR, generating a composite descriptor with both visual cues and spatial awareness based on a single camera. The key points lie in: 1) We use BEV features as an explicit source of structural knowledge in constructing global features. 2) The lower layers of the pre-trained backbone from BEV generation are shared for visual and structural streams in VPR, facilitating the learning of fine-grained local features in the visual stream. 3) The complementary visual and structural features can jointly enhance VPR performance. Our BEV2PR framework enables consistent performance improvements over several popular aggregation modules for RGB global features. The experiments on our collected VPR-NuScenes dataset demonstrate an absolute gain of 2.47% on Recall@1 for the strong Conv-AP baseline to achieve the best performance in our setting, and notably, a 18.06% gain on the hard set. The code and dataset will be available at https://github.com/FudongGe/BEV2PR.