HE-VPR: Height Estimation Enabled Aerial Visual Place Recognition Against Scale Variance
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915833960202240 |
|---|---|
| author | He, Mengfan Shao, Xingyu Li, Chunyu Chen, Chao Sun, Liangzheng Meng, Ziyang Wu, Yuanqing |
| author_facet | He, Mengfan Shao, Xingyu Li, Chunyu Chen, Chao Sun, Liangzheng Meng, Ziyang Wu, Yuanqing |
| contents | In this work, we propose HE-VPR, a visual place recognition (VPR) framework that incorporates height estimation. Our system decouples height inference from place recognition, allowing both modules to share a frozen DINOv2 backbone. Two lightweight bypass adapter branches are integrated into our system. The first estimates the height partition of the query image via retrieval from a compact height database, and the second performs VPR within the corresponding height-specific sub-database. The adaptation design reduces training cost and significantly decreases the search space of the database. We also adopt a center-weighted masking strategy to further enhance the robustness against scale differences. Experiments on two self-collected challenging multi-altitude datasets demonstrate that HE-VPR achieves up to 6.1\% Recall@1 improvement over state-of-the-art ViT-based baselines and reduces memory usage by up to 90\%. These results indicate that HE-VPR offers a scalable and efficient solution for height-aware aerial VPR, enabling practical deployment in GNSS-denied environments. All the code and datasets for this work have been released on https://github.com/hmf21/HE-VPR. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_04050 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | HE-VPR: Height Estimation Enabled Aerial Visual Place Recognition Against Scale Variance He, Mengfan Shao, Xingyu Li, Chunyu Chen, Chao Sun, Liangzheng Meng, Ziyang Wu, Yuanqing Robotics In this work, we propose HE-VPR, a visual place recognition (VPR) framework that incorporates height estimation. Our system decouples height inference from place recognition, allowing both modules to share a frozen DINOv2 backbone. Two lightweight bypass adapter branches are integrated into our system. The first estimates the height partition of the query image via retrieval from a compact height database, and the second performs VPR within the corresponding height-specific sub-database. The adaptation design reduces training cost and significantly decreases the search space of the database. We also adopt a center-weighted masking strategy to further enhance the robustness against scale differences. Experiments on two self-collected challenging multi-altitude datasets demonstrate that HE-VPR achieves up to 6.1\% Recall@1 improvement over state-of-the-art ViT-based baselines and reduces memory usage by up to 90\%. These results indicate that HE-VPR offers a scalable and efficient solution for height-aware aerial VPR, enabling practical deployment in GNSS-denied environments. All the code and datasets for this work have been released on https://github.com/hmf21/HE-VPR. |
| title | HE-VPR: Height Estimation Enabled Aerial Visual Place Recognition Against Scale Variance |
| topic | Robotics |
| url | https://arxiv.org/abs/2603.04050 |