Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives
Not on the map. Why?
Abstract (arXiv)
Cross-view feature matching aims to establish reliable correspondences across images with large viewpoint variations. Over the past decade, the field has evolved from task-specific models toward increasingly unified and generalizable correspondence models, with recent progress further driven by the emergence of vision foundation models (VFMs). Despite these advances, existing studies remain highly diverse in their problem formulations, model architectures, training paradigms, and evaluation protocols, making it difficult to obtain a unified understanding of the field. In this survey, we present a unified review of cross-view feature matching. We first introduce a structured taxonomy covering feature extraction, single-type feature matcher, multi-type feature matcher, VFMs based methods, training strategy and robust estimation, providing a coherent framework for analysis and comparison. We further examine recent advances, distilling key design principles and highlighting the shift toward unified and generalizable correspondence models. We also provide a unified experimental benchmarking of representative state-of-the-art methods under consistent protocols, enabling fair and comprehensive performance comparisons. In addition, we discuss open challenges and future directions, including efficiency, robustness under extreme conditions, and cross-domain generalization. This survey aims to provide a comprehensive and structured reference for understanding the evolution, current landscape, and future development of cross-view feature matching in the era of vision foundation models.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 108 of its 189 references that are in the map. First posted on arXiv 11 Aug 2026.
Builds on
108 of 189 references.
References · 108
- 2023Segment Anythingcited by 8,234
- 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
- 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,567
- 2025VGGT: Visual Geometry Grounded Transformercited by 1,539
- 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,443
- 2024Depth Anything V2cited by 1,422
- 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,320
- 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 984
- 2024Grounding Image Matching in 3D with MASt3Rcited by 983
- 2015NetVLAD: CNN architecture for weakly supervised place recognitioncited by 941
- 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 737
- 2023LightGlue: Local Feature Matching at Light Speedcited by 590
38 more
- 2018From Coarse to Fine: Robust Hierarchical Localization at Large Scalecited by 559
- 2023Emergent Correspondence from Image Diffusioncited by 446
- 2019D2-Net: A Trainable CNN for Joint Detection and Description of Local Featurescited by 326
- 2020DISK: Learning local features with policy gradientcited by 312
- 2016LIFT: Learned Invariant Feature Transformcited by 306
- 2023RoMa: Robust Dense Feature Matchingcited by 302
- 2016DSAC - Differentiable RANSAC for Camera Localizationcited by 266
- 2017HPatches: A benchmark and evaluation of handcrafted and learned local descriptorscited by 264
- 2017Working hard to know your neighbor's margins: Local descriptor learning losscited by 212
- 2022DKM: Dense Kernelized Feature Matching for Geometry Estimationcited by 177
- 2022ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformercited by 171
- 2019Learning Two-View Correspondences and Geometry Using Order-Aware Networkcited by 149
- 2019GLU-Net: Global-Local Universal Network for Dense Flow and Correspondencescited by 139
- 2017Convolutional neural network architecture for geometric matchingcited by 138
- 2017Graph-Cut RANSACcited by 133
- 2019SOSNet: Second Order Similarity Regularization for Local Descriptor Learningcited by 131
- 2019Neural-Guided RANSAC: Learning Where to Sample Model Hypothesescited by 129
- 2020Patch2Pix: Epipolar-Guided Pixel-Level Correspondencescited by 129
- 2022MatchFormer: Interleaving Attention in Transformers for Feature Matchingcited by 126
- 2024Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speedcited by 120
- 2019Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filterscited by 118
- 2021Learning Accurate Dense Correspondences and When to Trust Themcited by 113
- 2024XFeat: Accelerated Features for Lightweight Image Matchingcited by 113
- 2021Learning to Match Features with Seeded Graph Matching Networkcited by 92
- 2019ContextDesc: Local Descriptor Augmentation with Cross-Modality Contextcited by 79
- 2021ALIKE: Accurate and Lightweight Keypoint Detection and Descriptor Extractioncited by 77
- 2018Robust Estimation via Robust Gradient Estimationcited by 76
- 2024GIM: Learning Generalizable Image Matcher From Internet Videoscited by 75
- 2018DGC-Net: Dense Geometric Correspondence Networkcited by 67
- 2023GlueStick: Robust Image Matching by Sticking Points and Lines Togethercited by 66
- 2022ClusterGNN: Cluster-based Coarse-to-Fine Graph Neural Network for Efficient Feature Matchingcited by 62
- 2024OmniGlue: Generalizable Feature Matching with Foundation Model Guidancecited by 56
- 2014TILDE: A Temporally Invariant Learned DEtectorcited by 55
- 2020GOCor: Bringing Globally Optimized Correspondence Volumes into Your Neural Networkcited by 53
- 2018GeoDesc: Learning Local Descriptors by Integrating Geometry Constraintscited by 52
- 2025RoMa v2: Harder Better Faster Denser Feature Matchingcited by 51
- 2024MINIMA: Modality Invariant Image Matchingcited by 47
- 2021Progressive Correspondence Pruning by Consensus Learningcited by 46
50 most cited of 108 All 108 (JSON)
Built on by
Not cited yet.