| Pair-VPR: Place-Aware Pre-training and Contrastive Pair Classification for Visual Place Recognition with Vision Transformers | ✓ Link | 100 | 100 | 100 | Pair-VPR-p | 2024-10-09 |
| EffoVPR: Effective Foundation Model Utilization for Visual Place Recognition | | 98.7 | 98.7 | 98.7 | EffoVPR | 2024-05-28 |
| AdaptVPR: Route-Aware Hard Positive Generation for Robust Visual Place Recognition | ✓ Link | 98.7 | | | SALAD-DINOv3-B + AdaptVPR | 2026-09-03 |
| SelaVPR++: Towards Seamless Adaptation of Foundation Models for Efficient Place Recognition | ✓ Link | 98.4 | | | SelaVPR++ (DINOv2-L, rerank50) | 2025-02-23 |
| Focus on Local: Finding Reliable Discriminative Regions for Visual Place Recognition | ✓ Link | 98.4 | 99.1 | 99.4 | FoL | 2025-04-14 |
| Query-Based Adaptive Aggregation for Multi-Dataset Joint Training Toward Universal Visual Place Recognition | | 98.4 | | | QAA-DINOv2-B-8192 | 2025-07-04 |
| BoQ: A Place is Worth a Bag of Learnable Queries | ✓ Link | 98.1 | 98.1 | 98.7 | BoQ | 2024-05-12 |
| Pair-VPR: Place-Aware Pre-training and Contrastive Pair Classification for Visual Place Recognition with Vision Transformers | ✓ Link | 98.1 | 98.4 | 98.7 | Pair-VPR-s | 2024-10-09 |
| SAGE: Spatial-visual Adaptive Graph Exploration for Efficient Visual Place Recognition | ✓ Link | 98.1 | | | SAGE ViT-L (without cross-image encoder) | 2025-09-30 |
| Region Matters: Efficient and Reliable Region-Aware Visual Place Recognition | ✓ Link | 98.1 | | | FoL++ (ViT-L,reranking,322px) | 2026-04-24 |
| UniPR-3D: Towards Universal Visual Place Recognition with Visual Geometry Grounded Transformer | ✓ Link | 97.9 | | | UniPR-3D* (MegaLoc training setting, single frame) | 2025-12-24 |
| SuperPlace: The Renaissance of Classical Feature Aggregation for Visual Place Recognition in the Era of Foundation Models | ✓ Link | 97.8 | | | SuperPlace NVL-FT2 (DINOv2-B, GSV-Cities, 8192D, 322px) | 2025-06-16 |
| VLAD-BuFF: Burst-aware Fast Feature Aggregation for Visual Place Recognition | ✓ Link | 97.5 | | | VLAD-BuFF (PrePool192,PCA whitening4096D) | 2024-09-28 |
| EDTformer: An Efficient Decoder Transformer for Visual Place Recognition | ✓ Link | 97.1 | | | EDTformer (4096D, 2decoder blocks, 64learned tokens, LoPA rank4) | 2024-12-01 |
| Towards Implicit Aggregation: Robust Image Representation for Place Recognition in the Transformer Era | ✓ Link | 97.1 | | | ImAge (6144D, unified dataset) | 2025-11-08 |
| MegaLoc: One Retrieval to Place Them All | ✓ Link | 96.5 | | | MegaLoc (8448D) | 2025-02-24 |
| Focus on Local: Finding Reliable Discriminative Regions for Visual Place Recognition | ✓ Link | 96.2 | 98.7 | 98.7 | FoL-global | 2025-04-14 |
| Towards Seamless Adaptation of Pre-trained Models for Visual Place Recognition | ✓ Link | 94.0 | 97.5 | 96.8 | SelaVPR | 2024-02-22 |
| EigenPlaces: Training Viewpoint Robust Models for Visual Place Recognition | ✓ Link | 93 | | | EigenPlaces | 2023-08-21 |
| CricaVPR: Cross-image Correlation-aware Representation Learning for Visual Place Recognition | ✓ Link | 89.5 | | | CricaVPR (inference batch1,10752D) | 2024-02-29 |
| $R^{2}$Former: Unified $R$etrieval and $R$eranking Transformer for Place Recognition | ✓ Link | 88.6 | | | R2Former (ViT-Small, Pitts30k-finetuned, top-100 reranking) | 2023-04-06 |
| ProGEO: Generating Prompts through Image-Text Contrastive Learning for Visual Geo-localization | ✓ Link | 88.6 | 93.3 | | ProGEO | 2024-06-04 |
| TeTRA-VPR: A Ternary Transformer Approach for Compact Visual Place Recognition | ✓ Link | 88.6 | | | TeTRA-BoQ (ternary ViT, binary descriptor) | 2025-03-04 |
| Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition | ✓ Link | 86 | 88.6 | 90.5 | Patch-NetVLAD | 2021-03-02 |
| Self-supervising Fine-grained Region Similarities for Large-scale Image Localization | ✓ Link | 85.4 | | | SFRS | 2020-06-06 |
| Rethinking Visual Geo-localization for Large-Scale Applications | ✓ Link | 82.2 | | | CosPlace | 2022-04-05 |
| Stochastic Attraction-Repulsion Embedding for Large Scale Image Localization | ✓ Link | 80.63 | | | SARE Joint | 2018-08-27 |
| Learned Contextual Feature Reweighting for Image Geo-Localization | ✓ Link | 75.2 | | | CRN (VGG16, TokyoTimeMachine training) | 2017-07-01 |
| Semantic Reinforced Attention Learning for Visual Place Recognition | | 72.1 | | | SRALNet-SC (VGG16, 4096D PCA-whitened) | 2021-08-19 |
| NetVLAD: CNN architecture for weakly supervised place recognition | ✓ Link | 71.7 | | | NetVLAD (VGG-16, whitening 4096-D) | 2015-11-23 |
| Generalized Contrastive Optimization of Siamese Networks for Place Recognition | ✓ Link | 69.84 | 84.76 | 80.63 | GCL [trained only on MSLS] | 2021-03-11 |
| Rethinking Visual Geo-localization for Large-Scale Applications | ✓ Link | | 95.9 | 96.5 | CosPlace (ResNet-101 2048-D) | 2022-04-05 |
| Attention-based Pyramid Aggregation Network for Visual Place Recognition | | 66.98 | | | APANet (VGG-16, PCA-pw) | 2018-08-01 |