# Learning to Compare Image Patches via Convolutional Neural Networks

arXiv: https://arxiv.org/abs/1504.03641 · HTML: https://mlsanity.com/paper/1504.03641/

## Key facts

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

## Built on by (most cited first, 30 of 109)

- [UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction](https://mlsanity.com/paper/2104.10078/) (2021)
- [MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction](https://mlsanity.com/paper/2206.00665/) (2022)
- [NeuSG: Neural Implicit Surface Reconstruction with 3D Gaussian Splatting Guidance](https://mlsanity.com/paper/2312.00846/) (2023)
- [STMTrack: Template-free Visual Tracking with Space-time Memory Networks](https://mlsanity.com/paper/2104.00324/) (2021)
- [Unsupervised Object-Level Representation Learning from Scene Images](https://mlsanity.com/paper/2106.11952/) (2021)
- [Learning by Aligning: Visible-Infrared Person Re-identification using Cross-Modal Correspondences](https://mlsanity.com/paper/2108.07422/) (2021)
- [Spatially Consistent Representation Learning](https://mlsanity.com/paper/2103.06122/) (2021)
- [Multiview Stereo with Cascaded Epipolar RAFT](https://mlsanity.com/paper/2205.04502/) (2022)
- [VCR-GauS: View Consistent Depth-Normal Regularizer for Gaussian Surface Reconstruction](https://mlsanity.com/paper/2406.05774/) (2024)
- [CROSSFIRE: Camera Relocalization On Self-Supervised Features from an Implicit Representation](https://mlsanity.com/paper/2303.04869/) (2023)
- [UnsupervisedR&R: Unsupervised Point Cloud Registration via Differentiable Rendering](https://mlsanity.com/paper/2102.11870/) (2021)
- [Neural Markov Random Field for Stereo Matching](https://mlsanity.com/paper/2403.11193/) (2024)
- [Detect and Locate: Exposing Face Manipulation by Semantic- and Noise-level Telltales](https://mlsanity.com/paper/2107.05821/) (2021)
- [TINYCD: A (Not So) Deep Learning Model For Change Detection](https://mlsanity.com/paper/2207.13159/) (2022)
- [Enabling Country-Scale Land Cover Mapping with Meter-Resolution Satellite Imagery](https://mlsanity.com/paper/2209.00727/) (2022)
- [GaussianRoom: Improving 3D Gaussian Splatting with SDF Guidance and Monocular Cues for Indoor Scene Reconstruction](https://mlsanity.com/paper/2405.19671/) (2024)
- [Dual Contrastive Loss and Attention for GANs](https://mlsanity.com/paper/2103.16748/) (2021)
- [OpenStereo: A Comprehensive Benchmark for Stereo Matching and Strong Baseline](https://mlsanity.com/paper/2312.00343/) (2023)
- [HIER: Metric Learning Beyond Class Labels via Hierarchical Regularization](https://mlsanity.com/paper/2212.14258/) (2022)
- [HSCNet++: Hierarchical Scene Coordinate Classification and Regression for Visual Localization with Transformer](https://mlsanity.com/paper/2305.03595/) (2023)
- [FCCDN: Feature Constraint Network for VHR Image Change Detection](https://mlsanity.com/paper/2105.10860/) (2021)
- [AVA-AVD: Audio-Visual Speaker Diarization in the Wild](https://mlsanity.com/paper/2111.14448/) (2021)
- [DFM: A Performance Baseline for Deep Feature Matching](https://mlsanity.com/paper/2106.07791/) (2021)
- [Stereoscopic Universal Perturbations across Different Architectures and Datasets](https://mlsanity.com/paper/2112.06116/) (2021)
- [RankSRGAN: Super Resolution Generative Adversarial Networks with Learning to Rank](https://mlsanity.com/paper/2107.09427/) (2021)
- [Self-Taught Metric Learning without Labels](https://mlsanity.com/paper/2205.01903/) (2022)
- [BotTriNet: A Unified and Efficient Embedding for Social Bots Detection via Metric Learning](https://mlsanity.com/paper/2304.03144/) (2023)
- [HumanGPS: Geodesic PreServing Feature for Dense Human Correspondences](https://mlsanity.com/paper/2103.15573/) (2021)
- [Deep Multi-View Stereo gone wild](https://mlsanity.com/paper/2104.15119/) (2021)
- [Multimodal Representation for Neural Code Search](https://mlsanity.com/paper/2107.00992/) (2021)

## 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.