| BoQ: A Place is Worth a Bag of Learnable Queries | ✓ Link | 100.0 | 100 | | BoQ
(DINOv2) | 2024-05-12 |
| EffoVPR: Effective Foundation Model Utilization for Visual Place Recognition | | 100.0 | 100.0 | | EffoVPR | 2024-05-28 |
| VLAD-BuFF: Burst-aware Fast Feature Aggregation for Visual Place Recognition | ✓ Link | 100 | 100 | | VLAD-BuFF (PCA whitening,8192D) | 2024-09-28 |
| Focus on Local: Finding Reliable Discriminative Regions for Visual Place Recognition | ✓ Link | 99.9 | 100 | 100 | FoL-global | 2025-04-14 |
| Focus on Local: Finding Reliable Discriminative Regions for Visual Place Recognition | ✓ Link | 99.9 | 100 | 100 | FoL | 2025-04-14 |
| Towards Implicit Aggregation: Robust Image Representation for Place Recognition in the Transformer Era | ✓ Link | 99.9 | 100 | | ImAge (6144D, GSV-Cities) | 2025-11-08 |
| Towards Seamless Adaptation of Pre-trained Models for Visual Place Recognition | ✓ Link | 99.8 | | | SelaVPR | 2024-02-22 |
| $R^{2}$Former: Unified $R$etrieval and $R$eranking Transformer for Place Recognition | ✓ Link | 99.7 | | | R2Former (ViT-Small, MSLS-trained, top-100 reranking) | 2023-04-06 |
| ProGEO: Generating Prompts through Image-Text Contrastive Learning for Visual Geo-localization | ✓ Link | 99.7 | 99.9 | | ProGEO | 2024-06-04 |
| MixVPR: Feature Mixing for Visual Place Recognition | ✓ Link | 99.66 | | | MixVPR | 2023-03-03 |
| EigenPlaces: Training Viewpoint Robust Models for Visual Place Recognition | ✓ Link | 99.6 | 99.9 | 100 | EigenPlaces (ResNet-50, 2048D) | 2023-08-21 |
| Rethinking Visual Geo-localization for Large-Scale Applications | ✓ Link | 99.59 | 99.9 | | CosPlace | 2022-04-05 |
| Deep Homography Estimation for Visual Place Recognition | ✓ Link | 99.1 | 99.6 | 99.7 | DHE-VPR (jointly fine-tuned) | 2024-02-25 |
| AnyLoc: Towards Universal Visual Place Recognition | ✓ Link | 96.17 | | | AnyLoc-VLAD-DINOv2 | 2023-08-01 |
| DINOv2: Learning Robust Visual Features without Supervision | ✓ Link | 78.62 | | | DINOv2 | 2023-04-14 |
| AnyLoc: Towards Universal Visual Place Recognition | ✓ Link | 62.7 | | | CLIP | 2023-08-01 |
| NetVLAD: CNN architecture for weakly supervised place recognition | ✓ Link | 57.92 | | | NetVLAD | 2015-11-23 |
| Emerging Properties in Self-Supervised Vision Transformers | ✓ Link | 45.22 | | | DINO | 2021-04-29 |
| BoQ: A Place is Worth a Bag of Learnable Queries | ✓ Link | | 100 | 100 | BoQ | 2024-05-12 |