| Query-Based Adaptive Aggregation for Multi-Dataset Joint Training Toward Universal Visual Place Recognition | | 85.7 | | | QAA-DINOv2-B-8192 | 2025-07-04 |
| SuperPlace: The Renaissance of Classical Feature Aggregation for Visual Place Recognition in the Era of Foundation Models | ✓ Link | 84.8 | | 94.2 | SuperPlace SP-NVL-FT2 (DINOv2-L, GPMS, 8192D, 322px) | 2025-06-16 |
| Towards Implicit Aggregation: Robust Image Representation for Place Recognition in the Transformer Era | ✓ Link | 84.5 | 93.8 | 95.4 | ImAge | 2025-11-08 |
| SelaVPR++: Towards Seamless Adaptation of Foundation Models for Efficient Place Recognition | ✓ Link | 84 | 93.7 | 94.4 | SelaVPR++ (DINOv2-L, binary512D + float4096D, rerank100) | 2025-02-23 |
| "Close, But Not There: Boosting Geographic Distance Sensitivity in Visual Place Recognition" | ✓ Link | 82.7 | 91.2 | 92.7 | DINOv2 SALAD + CliqueMining | 2024-07-02 |
| Pair-VPR: Place-Aware Pre-training and Contrastive Pair Classification for Visual Place Recognition with Vision Transformers | ✓ Link | 81.7 | 90.2 | 91.3 | Pair-VPR-p | 2024-10-09 |
| DC-VLAQ: Query-Residual Aggregation for Robust Visual Place Recognition | | 81.7 | 92.2 | 94.5 | DC-VLAQ | 2026-01-19 |
| A^2GC: Asymmetric Aggregation with Geometric Constraints for Locally Aggregated Descriptors | ✓ Link | 80.6 | 90.9 | 92.5 | A²GC (DINOv2-G, 33280-D) | 2025-11-18 |
| Focus on Local: Finding Reliable Discriminative Regions for Visual Place Recognition | ✓ Link | 80.0 | 90.9 | 93.0 | FoL | 2025-04-14 |
| BoQ: A Place is Worth a Bag of Learnable Queries | ✓ Link | 79 | 90.3 | 92 | BoQ | 2024-05-12 |
| EffoVPR: Effective Foundation Model Utilization for Visual Place Recognition | | 79.0 | 89.0 | 91.6 | EffoVPR | 2024-05-28 |
| Pair-VPR: Place-Aware Pre-training and Contrastive Pair Classification for Visual Place Recognition with Vision Transformers | ✓ Link | 79.0 | 86.9 | 88.3 | Pair-VPR-s | 2024-10-09 |
| Focus on Local: Finding Reliable Discriminative Regions for Visual Place Recognition | ✓ Link | 78.7 | 90.8 | 93.0 | FoL-global | 2025-04-14 |
| EDTformer: An Efficient Decoder Transformer for Visual Place Recognition | ✓ Link | 78.4 | 89.8 | 91.9 | EDTformer (4096D, 2decoder blocks, 64learned tokens, LoPA rank4) | 2024-12-01 |
| Faster or Stronger: Towards Flexible Visual Place Recognition via Weighted Aggregation and Token Pruning | | 76.3 | 87.9 | | WeiAD + WeiToP (DINOv2 ViT-B, retention 0.95) | 2026-05-19 |
| UniPR-3D: Towards Universal Visual Place Recognition with Visual Geometry Grounded Transformer | ✓ Link | 75.9 | | 91.8 | UniPR-3D* (MegaLoc training setting, single frame) | 2025-12-24 |
| Optimal Transport Aggregation for Visual Place Recognition | ✓ Link | 75 | 88.8 | 91.3 | DINOv2 SALAD | 2023-11-27 |
| LaVPR: Benchmarking Language and Vision for Place Recognition | ✓ Link | 74.6 | 88.8 | 91.2 | La-SALAD+BGE-L (ADS+LLP) [Gemini2.5Flash image captions] | 2026-02-03 |
| Towards Seamless Adaptation of Pre-trained Models for Visual Place Recognition | ✓ Link | 73.5 | 87.5 | 90.6 | SelaVPR | 2024-02-22 |
| $R^{2}$Former: Unified $R$etrieval and $R$eranking Transformer for Place Recognition | ✓ Link | 73 | 85.9 | 88.8 | R2Former (ViT-Small, MSLS-trained, top-100 reranking) | 2023-04-06 |
| StructVPR++: Distill Structural and Semantic Knowledge with Weighting Samples for Visual Place Recognition | ✓ Link | 72.5 | 85.1 | 87.9 | StructVPR++ + SuperPoint-SuperGlue (top100 reranking) | 2025-03-09 |
| StructVPR++: Distill Structural and Semantic Knowledge with Weighting Samples for Visual Place Recognition | ✓ Link | 65.7 | | 85.3 | StructVPR++ (global retrieval) | 2025-03-09 |
| MixVPR: Feature Mixing for Visual Place Recognition | ✓ Link | 64.0 | 75.9 | 80.6 | MixVPR | 2023-03-03 |
| Generalized Contrastive Optimization of Siamese Networks for Place Recognition | ✓ Link | 62.3 | 76.2 | 81.1 | ResNeXt-GCL-PCA | 2021-03-11 |
| Deep Homography Estimation for Visual Place Recognition | ✓ Link | 61.7 | 78.2 | 82.6 | DHE-VPR (jointly fine-tuned) | 2024-02-25 |
| Generalized Contrastive Optimization of Siamese Networks for Place Recognition | ✓ Link | 56.0 | 70.8 | 75.1 | RexNeXt-GCL | 2021-03-11 |
| UniPR-3D: Towards Universal Visual Place Recognition with Visual Geometry Grounded Transformer | ✓ Link | | 87.5 | | UniPR-3D (GSV-Cities single-frame release) | 2025-12-24 |
| SuperPlace: The Renaissance of Classical Feature Aggregation for Visual Place Recognition in the Era of Foundation Models | ✓ Link | | 93.5 | | SuperPlace SALAD-SLA (DINOv2-B, GSV-Cities+MSLS, 8448D, 224px) | 2025-06-16 |
| Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition | ✓ Link | 48.1 | 57.6 | 60.5 | Patch-NetVLAD (Multi-RANSAC, 4096-D) | 2021-03-02 |