mlsanityData to 7 Oct 2026

MegaLoc: One Retrieval to Place Them All

arXiv 2502.17237 ↗First posted 24 Feb 2025cs.CVcited by 58

Not on the map. Why?

Abstract (arXiv)

Retrieving images from the same location as a given query is an important component of multiple computer vision tasks, like Visual Place Recognition, Landmark Retrieval, Visual Localization, 3D reconstruction, and SLAM. However, existing solutions are built to specifically work for one of these tasks, and are known to fail when the requirements slightly change or when they meet out-of-distribution data. In this paper we combine a variety of existing methods, training techniques, and datasets to train a retrieval model, called MegaLoc, that is performant on multiple tasks. We find that MegaLoc (1) achieves state of the art on a large number of Visual Place Recognition datasets, (2) impressive results on common Landmark Retrieval datasets, and (3) sets a new state of the art for Visual Localization on the LaMAR datasets, where we only changed the retrieval method to the existing localization pipeline. The code for MegaLoc is available at https://github.com/gmberton/MegaLoc

Key facts. Cited by 58 papers in the map (data through 7 Oct 2026). Builds on 23 of its 40 references that are in the map. First posted on arXiv 24 Feb 2025.

Builds on

23 of 40 references.

References · 23

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  4. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
  5. 2015NetVLAD: CNN architecture for weakly supervised place recognitioncited by 935
  6. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 731
  7. 2018From Coarse to Fine: Robust Hierarchical Localization at Large Scalecited by 556
  8. 2019Multi-Similarity Loss with General Pair Weighting for Deep Metric Learningcited by 368
  9. 2020Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrievalcited by 305
  10. 2024Global Structure-from-Motion Revisitedcited by 215
  11. 2018Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarkingcited by 189
  12. 2019Learning with Average Precision: Training Image Retrieval with a Listwise Losscited by 184
11 more
  1. 2023MixVPR: Feature Mixing for Visual Place Recognitioncited by 160
  2. 2023AnyLoc: Towards Universal Visual Place Recognitioncited by 159
  3. 2023Optimal Transport Aggregation for Visual Place Recognitioncited by 151
  4. 2023EigenPlaces: Training Viewpoint Robust Models for Visual Place Recognitioncited by 109
  5. 2022LaMAR: Benchmarking Localization and Mapping for Augmented Realitycited by 98
  6. 2022GSV-Cities: Toward Appropriate Supervised Visual Place Recognitioncited by 92
  7. 2022Deep Visual Geo-localization Benchmarkcited by 83
  8. 2024CricaVPR: Cross-image Correlation-aware Representation Learning for Visual Place Recognitioncited by 61
  9. 2024MegaScenes: Scene-Level View Synthesis at Scalecited by 58
  10. 2024Close, But Not There: Boosting Geographic Distance Sensitivity in Visual Place Recognitioncited by 27
  11. 2023Are Local Features All You Need for Cross-Domain Visual Place Recognition?cited by 21

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 17; 2026: 41.

58 papers.

Sort:

By area:

  1. 2025Emergent Outlier View Rejection in Visual Geometry Grounded Transformerscited by 19
  2. 2025Scaling Image Geo-Localization to Continent Levelcited by 10
  3. 2025Seeing in the Dark: Benchmarking Egocentric 3D Vision with the Oxford Day-and-Night Datasetcited by 8
  4. 2025UniPR-3D: Towards Universal Visual Place Recognition with Visual Geometry Grounded Transformercited by 8
  5. 2026Global Structure-from-Motion Meets Feedforward Reconstructioncited by 6
  6. 2025Ensemble-Based Event Camera Place Recognition Under Varying Illuminationcited by 4
  7. 2025Image-Based Relocalization and Alignment for Long-Term Monitoring of Dynamic Underwater Environmentscited by 3
  8. 2025To Match or Not to Match: Revisiting Image Matching for Reliable Visual Place Recognitioncited by 3
  9. 2026AirZoo: A Unified Large-Scale Dataset for Grounding Aerial Geometric 3D Visioncited by 3
  10. 2025SAGE: Spatial-visual Adaptive Graph Exploration for Efficient Visual Place Recognitioncited by 2
  11. 2025UniMPR: A Unified Framework for Multimodal Place Recognition with Heterogeneous Sensor Configurationscited by 2
  12. 2026TIGeR: A Unified Framework for Time, Images and Geo-location Retrievalcited by 2
38 more
  1. 2026MV-RoMa: From Pairwise Matching into Multi-View Track Reconstructioncited by 2
  2. 2026Event-Driven Neuromorphic Vision Enables Energy-Efficient Visual Place Recognitioncited by 2
  3. 2026Region Matters: Efficient and Reliable Region-Aware Visual Place Recognitioncited by 2
  4. 2026Diversity-aware View Partitioning for Scalable VGGTcited by 2
  5. 2026VidMap: Exploiting Temporal Structure for Video-Based Structure-from-Motioncited by 2
  6. 2025Query-Based Adaptive Aggregation for Multi-Dataset Joint Training Toward Universal Visual Place Recognitioncited by 1
  7. 2026ImLoc: Revisiting Visual Localization with Image-based Representationcited by 1
  8. 2026Quantile Transfer for Reliable Operating Point Selection in Visual Place Recognitioncited by 1
  9. 2026Global-Aware Edge Prioritization for Pose Graph Initializationcited by 1
  10. 2026EventGeM: Global-to-Local Feature Matching for Event-Based Visual Place Recognitioncited by 1
  11. 2025Hi^2-GSLoc: Dual-Hierarchical Gaussian-Specific Visual Relocalization for Remote Sensingcited by 0
  12. 2025TOPO-Bench: An Open-Source Topological Mapping Evaluation Framework with Quantifiable Perceptual Aliasingcited by 0
  13. 2025Joint Multi-Condition Representation Modelling via Matrix Factorisation for Visual Place Recognitioncited by 0
  14. 2025Beyond Paired Data: Self-Supervised UAV Geo-Localization from Reference Imagery Alonecited by 0
  15. 2025YOPO-Nav: Visual Navigation using 3DGS Graphs from One-Pass Videoscited by 0
  16. 2025Robust Scene Coordinate Regression via Geometrically-Consistent Global Descriptorscited by 0
  17. 2025MMLANDMARKS: a Cross-View Instance-Level Benchmark for Geo-Spatial Understandingcited by 0
  18. 2026OpenNavMap: Multi-Session Appearance-Based Topometric Mapping for Scalable Visual Navigationcited by 0
  19. 2026Hybrid Cross-Device Localization via Neural Metric Learning and Feature Fusioncited by 0
  20. 2026Long-Term Multi-Session 3D Reconstruction Under Substantial Appearance Changecited by 0
  21. 2026Automatic Map Density Selection for Locally-Performant Visual Place Recognitioncited by 0
  22. 2026Long-Term Visual Localization in Dynamic Benthic Environments: A Dataset, Footprint-Based Ground Truth, and Visual Place Recognition Benchmarkcited by 0
  23. 2026GloSplat: Joint Pose-Appearance Optimization for Faster and More Accurate 3D Reconstructioncited by 0
  24. 2026L3:Scene-agnostic Visual Localization in the Wildcited by 0
  25. 2026Evaluation of Visual Place Recognition Methods for Image Pair Retrieval in 3D Vision and Roboticscited by 0
  26. 2026MultiLoc: Look Around As You Localize for Fast And Robust Visual Re-localizationcited by 0
  27. 2026AsymLoc: Towards Asymmetric Feature Matching for Efficient Visual Localizationcited by 0
  28. 2026Good Token Hunting: A Hitchhiker's Guide to Token Selection for Visual Geometry Transformerscited by 0
  29. 2026DisPlace: Discriminative Place Projections for Multi-Reference Visual Place Recognitioncited by 0
  30. 2026One Channel to Rule Them All: Rethinking Input Representation for Visual Place Recognitioncited by 0
  31. 2026Dash2Sim: Closed-Loop Driving Simulation from in-the-wild Dashcam Videoscited by 0
  32. 2026SG2Loc: Sequential Visual Localization on 3D Scene Graphscited by 0
  33. 2026From Open Waters to Enclosed Cabins: ProteusVPR for Cross-Scene Visual Place Recognition in Maritime Perception and Cabin Inspectioncited by 0
  34. 2026Reference-Induced Consensus for Selective Posed-Reference Visual Localizationcited by 0
  35. 2026DGSfM: Depth-Guided Scale-Aware Global Structure-from-Motioncited by 0
  36. 2026Selectivity Drives Efficiency: Dataset Pruning for Visual Place Recognitioncited by 0
  37. 2026Accuracy potential of visual localization exploiting high-end street-level imagerycited by 0
  38. 2026Are Visual Place Recognition Models Recognizing Places or Conditions? Distractor-Augmented Evaluation and Condition Suppressioncited by 0

50 most cited of 58 All 58 (JSON)