mlsanityData to 7 Oct 2026

Learning to Compare Image Patches via Convolutional Neural Networks

arXiv 1504.03641 ↗First posted 14 Apr 2015cs.CV cs.LG cs.NEcited by 109

Not on the map. Why?

Abstract (arXiv)

In this paper we show how to learn directly from image data (i.e., without resorting to manually-designed features) a general similarity function for comparing image patches, which is a task of fundamental importance for many computer vision problems. To encode such a function, we opt for a CNN-based model that is trained to account for a wide variety of changes in image appearance. To that end, we explore and study multiple neural network architectures, which are specifically adapted to this task. We show that such an approach can significantly outperform the state-of-the-art on several problems and benchmark datasets.

Key facts. Cited by 109 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 Apr 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 40; 2022: 17; 2023: 26; 2024: 16; 2025: 8; 2026: 2.

109 papers.

Sort:

By area:

  1. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 643
  2. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 467
  3. 2023NeuSG: Neural Implicit Surface Reconstruction with 3D Gaussian Splatting Guidancecited by 137
  4. 2021STMTrack: Template-free Visual Tracking with Space-time Memory Networkscited by 91
  5. 2021Unsupervised Object-Level Representation Learning from Scene Imagescited by 72
  6. 2021Learning by Aligning: Visible-Infrared Person Re-identification using Cross-Modal Correspondencescited by 66
  7. 2021Spatially Consistent Representation Learningcited by 64
  8. 2022Multiview Stereo with Cascaded Epipolar RAFTcited by 51
  9. 2024VCR-GauS: View Consistent Depth-Normal Regularizer for Gaussian Surface Reconstructioncited by 50
  10. 2023CROSSFIRE: Camera Relocalization On Self-Supervised Features from an Implicit Representationcited by 45
  11. 2021UnsupervisedR&R: Unsupervised Point Cloud Registration via Differentiable Renderingcited by 44
  12. 2021Detect and Locate: Exposing Face Manipulation by Semantic- and Noise-level Telltalescited by 39
38 more
  1. 2024Neural Markov Random Field for Stereo Matchingcited by 38
  2. 2022TINYCD: A (Not So) Deep Learning Model For Change Detectioncited by 35
  3. 2022Enabling Country-Scale Land Cover Mapping with Meter-Resolution Satellite Imagerycited by 31
  4. 2024GaussianRoom: Improving 3D Gaussian Splatting with SDF Guidance and Monocular Cues for Indoor Scene Reconstructioncited by 31
  5. 2021Dual Contrastive Loss and Attention for GANscited by 30
  6. 2023OpenStereo: A Comprehensive Benchmark for Stereo Matching and Strong Baselinecited by 28
  7. 2022HIER: Metric Learning Beyond Class Labels via Hierarchical Regularizationcited by 26
  8. 2023HSCNet++: Hierarchical Scene Coordinate Classification and Regression for Visual Localization with Transformercited by 26
  9. 2021FCCDN: Feature Constraint Network for VHR Image Change Detectioncited by 25
  10. 2021AVA-AVD: Audio-Visual Speaker Diarization in the Wildcited by 24
  11. 2021DFM: A Performance Baseline for Deep Feature Matchingcited by 17
  12. 2021Stereoscopic Universal Perturbations across Different Architectures and Datasetscited by 17
  13. 2021RankSRGAN: Super Resolution Generative Adversarial Networks with Learning to Rankcited by 13
  14. 2022Self-Taught Metric Learning without Labelscited by 13
  15. 2023BotTriNet: A Unified and Efficient Embedding for Social Bots Detection via Metric Learningcited by 13
  16. 2021HumanGPS: Geodesic PreServing Feature for Dense Human Correspondencescited by 12
  17. 2021Deep Multi-View Stereo gone wildcited by 11
  18. 2021Multimodal Representation for Neural Code Searchcited by 11
  19. 2021FADNet++: Real-Time and Accurate Disparity Estimation with Configurable Networkscited by 11
  20. 2021Dr-Vectors: Decision Residual Networks and an Improved Loss for Speaker Recognitioncited by 10
  21. 2023Learning a Room with the Occ-SDF Hybrid: Signed Distance Function Mingled with Occupancy Aids Scene Representationcited by 10
  22. 2021Camera Invariant Feature Learning for Generalized Face Anti-spoofingcited by 9
  23. 2022Multi-View Reconstruction using Signed Ray Distance Functions (SRDF)cited by 9
  24. 2023SAME++: A Self-supervised Anatomical eMbeddings Enhanced medical image registration framework using stable sampling and regularized transformationcited by 9
  25. 2021Matching in the Dark: A Dataset for Matching Image Pairs of Low-light Scenescited by 7
  26. 2022A Critical Analysis of Image-based Camera Pose Estimation Techniquescited by 7
  27. 2022Learning-Based Dimensionality Reduction for Computing Compact and Effective Local Feature Descriptorscited by 7
  28. 2023DiViNeT: 3D Reconstruction from Disparate Views via Neural Template Regularizationcited by 7
  29. 2024Use of Graph Neural Networks in Aiding Defensive Cyber Operationscited by 7
  30. 2025Deep Learning Reforms Image Matching: A Survey and Outlookcited by 7
  31. 2022Urban Change Forecasting from Satellite Imagescited by 6
  32. 2021Improving Deep Metric Learning by Divide and Conquercited by 5
  33. 2022Deep Rank-Consistent Pyramid Model for Enhanced Crowd Countingcited by 5
  34. 2023Image Patch-Matching with Graph-Based Learning in Street Scenescited by 5
  35. 2024Extending 6D Object Pose Estimators for Stereo Visioncited by 5
  36. 2021A Survey on Active Deep Learning: From Model-driven to Data-drivencited by 4
  37. 2021A Fusion-Denoising Attack on InstaHide with Data Augmentationcited by 4
  38. 2021Multi-Head Deep Metric Learning Using Global and Local Representationscited by 4

50 most cited of 109 All 109 (JSON)