| UniPR-3D: Towards Universal Visual Place Recognition with Visual Geometry Grounded Transformer | ✓ Link | 95.9 | | 99.3 | UniPR-3D* (MegaLoc training setting, single frame) | 2025-12-24 |
| A^2GC: Asymmetric Aggregation with Geometric Constraints for Locally Aggregated Descriptors | ✓ Link | 95.2 | | | A²GC (DINOv2-B, 8448-D) | 2025-11-18 |
| Lost in the Tail: Addressing Geographic Imbalance in Urban Visual Place Recognition | | 95.2 | | | ImAge + LB loss | 2026-06-30 |
| Focus on Local: Finding Reliable Discriminative Regions for Visual Place Recognition | ✓ Link | 95 | | | FoL-global (ViT-L, 504x504) | 2025-04-14 |
| Optimal Transport Aggregation for Visual Place Recognition | ✓ Link | 94.8 | | | DINOv2 SALAD (8448D) | 2023-11-27 |
| MegaLoc: One Retrieval to Place Them All | ✓ Link | 94.8 | | 98.5 | MegaLoc (8448D) | 2025-02-24 |
| SAGE: Spatial-visual Adaptive Graph Exploration for Efficient Visual Place Recognition | ✓ Link | 94.8 | 98.3 | 99 | SAGE ViT-L (without cross-image encoder) | 2025-09-30 |
| Query-Based Adaptive Aggregation for Multi-Dataset Joint Training Toward Universal Visual Place Recognition | | 94.6 | | | QAA-DINOv2-B-8192 | 2025-07-04 |
| EffoVPR: Effective Foundation Model Utilization for Visual Place Recognition | | 94.5 | 98.2 | 97.8 | EffoVPR | 2024-05-28 |
| SuperPlace: The Renaissance of Classical Feature Aggregation for Visual Place Recognition in the Era of Foundation Models | ✓ Link | 94.1 | | | SuperPlace SP-NVL-FT2 (DINOv2-B, GPMS, 8192D, 322px) | 2025-06-16 |
| ProGEO: Generating Prompts through Image-Text Contrastive Learning for Visual Geo-localization | ✓ Link | 93.0 | 96.7 | | ProGEO | 2024-06-04 |
| EigenPlaces: Training Viewpoint Robust Models for Visual Place Recognition | ✓ Link | 90.8 | 95.7 | 96.7 | EigenPlaces | 2023-08-21 |
| Rethinking Visual Geo-localization for Large-Scale Applications | ✓ Link | 83.4 | 91.6 | 94.1 | CosPlace | 2022-04-05 |
| Focus on Local: Finding Reliable Discriminative Regions for Visual Place Recognition | ✓ Link | | 98.2 | | FoL-global (ViT-L, 322x322) | 2025-04-14 |
| Lost in the Tail: Addressing Geographic Imbalance in Urban Visual Place Recognition | | | 97 | 97.5 | DAPR-M (DINOv2, LB loss + CFD) | 2026-06-30 |