| EffoVPR: Effective Foundation Model Utilization for Visual Place Recognition | | 93.4 | | | EffoVPR-R (rerank top5, 504px) | 2024-05-28 |
| Faster or Stronger: Towards Flexible Visual Place Recognition via Weighted Aggregation and Token Pruning | | 93.1 | 97 | | WeiAD (DINOv2 ViT-L) | 2026-05-19 |
| SelaVPR++: Towards Seamless Adaptation of Foundation Models for Efficient Place Recognition | ✓ Link | 92.9 | | | SelaVPR++ (DINOv2-L, binary512D + float4096D, rerank100) | 2025-02-23 |
| VLAD-BuFF: Burst-aware Fast Feature Aggregation for Visual Place Recognition | ✓ Link | 92.8 | 96.2 | | VLAD-BuFF (PCA whitening,8192D) | 2024-09-28 |
| EDTformer: An Efficient Decoder Transformer for Visual Place Recognition | ✓ Link | 92.8 | | | EDTformer (4096D, LoPA rank2) | 2024-12-01 |
| UniPR-3D: Towards Universal Visual Place Recognition with Visual Geometry Grounded Transformer | ✓ Link | 92.8 | | 97.9 | UniPR-3D* (MegaLoc training setting, single frame) | 2025-12-24 |
| BoQ: A Place is Worth a Bag of Learnable Queries | ✓ Link | 92.5 | 95.9 | 96.7 | BoQ | 2024-05-12 |
| Optimal Transport Aggregation for Visual Place Recognition | ✓ Link | 92.1 | 96.2 | 96.5 | DINOv2 SALAD | 2023-11-27 |
| Focus on Local: Finding Reliable Discriminative Regions for Visual Place Recognition | ✓ Link | 92.1 | 96.5 | 98.0 | FoL-global | 2025-04-14 |
| SAGE: Spatial-visual Adaptive Graph Exploration for Efficient Visual Place Recognition | ✓ Link | 92.1 | 96.2 | 96.9 | SAGE ViT-L (without cross-image encoder) | 2025-09-30 |
| Focus on Local: Finding Reliable Discriminative Regions for Visual Place Recognition | ✓ Link | 91.8 | 96.5 | 97.4 | FoL | 2025-04-14 |
| Query-Based Adaptive Aggregation for Multi-Dataset Joint Training Toward Universal Visual Place Recognition | | 91.8 | | | QAA-DINOv2-B-8192 | 2025-07-04 |
| Towards Implicit Aggregation: Robust Image Representation for Place Recognition in the Transformer Era | ✓ Link | 91.6 | 95.6 | | ImAge (6144D, GSV-Cities) | 2025-11-08 |
| SuperPlace: The Renaissance of Classical Feature Aggregation for Visual Place Recognition in the Era of Foundation Models | ✓ Link | 87.5 | | | SuperPlace SP-NVL-FT2 (DINOv2-B, GPMS, 8192D, 322px) | 2025-06-16 |
| BoQ: A Place is Worth a Bag of Learnable Queries | ✓ Link | 86.5 | 93.4 | 95.7 | BoQ (ResNet-50) | 2024-05-12 |
| D²-VPR: A Parameter-efficient Visual-foundation-model-based Visual Place Recognition Method via Knowledge Distillation and Deformable Aggregation | ✓ Link | 86.2 | 93.2 | | D2-VPR (no encoder) | 2025-11-16 |
| MixVPR: Feature Mixing for Visual Place Recognition | ✓ Link | 85.2 | 92.1 | 94.6 | MixVPR | 2023-03-03 |
| A^2GC: Asymmetric Aggregation with Geometric Constraints for Locally Aggregated Descriptors | ✓ Link | 83.86 | 92.75 | 95.56 | A²GC (DINOv2-B) | 2025-11-18 |
| Structured Pruning for Efficient Visual Place Recognition | | 82 | | | GeM (structured pruning40%,gamma0.00) | 2024-09-12 |
| GSV-Cities: Toward Appropriate Supervised Visual Place Recognition | ✓ Link | 81.55 | 90.77 | | Conv-AP (released ResNet50,2048D) | 2022-10-19 |
| GSV-Cities: Toward Appropriate Supervised Visual Place Recognition | ✓ Link | | | 93.9 | Conv-AP (ResNet50,4x4 pooling) | 2022-10-19 |
| UniPR-3D: Towards Universal Visual Place Recognition with Visual Geometry Grounded Transformer | ✓ Link | | 94.5 | | UniPR-3D (GSV-Cities single-frame release) | 2025-12-24 |
| Global Proxy-based Hard Mining for Visual Place Recognition | ✓ Link | 79.4 | 90.6 | 93.2 | GPM (ResNet-50 NetVLAD, MS+OHM) | 2023-02-28 |
| D²-VPR: A Parameter-efficient Visual-foundation-model-based Visual Place Recognition Method via Knowledge Distillation and Deformable Aggregation | ✓ Link | | | 94.1 | D2-VPR (released no encoder) | 2025-11-16 |
| EDTformer: An Efficient Decoder Transformer for Visual Place Recognition | ✓ Link | | 96.9 | | EDTformer (4096D, LoPA rank24) | 2024-12-01 |
| EDTformer: An Efficient Decoder Transformer for Visual Place Recognition | ✓ Link | | | 96.9 | EDTformer (4096D, 2decoder blocks, 64learned tokens, LoPA rank4) | 2024-12-01 |
| EffoVPR: Effective Foundation Model Utilization for Visual Place Recognition | | | 97.9 | 98.4 | EffoVPR-R (1024D global + local reranking, 504px) | 2024-05-28 |