# Image Keypoint Matching using Graph Neural Networks

arXiv: https://arxiv.org/abs/2205.14275 · HTML: https://mlsanity.com/paper/2205.14275/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 31 references that are in the map.
- First posted on arXiv 27 May 2022.

## Builds on (most cited first, 16 of 16)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernels](https://mlsanity.com/paper/1711.08920/) (2017)
- [Gromov-Wasserstein Learning for Graph Matching and Node Embedding](https://mlsanity.com/paper/1901.06003/) (2019)
- [Learning Combinatorial Embedding Networks for Deep Graph Matching](https://mlsanity.com/paper/1904.00597/) (2019)
- [SimGNN: A Neural Network Approach to Fast Graph Similarity Computation](https://mlsanity.com/paper/1808.05689/) (2018)
- [Deep Graph Matching Consensus](https://mlsanity.com/paper/2001.09621/) (2020)
- [Universal Correspondence Network](https://mlsanity.com/paper/1606.03558/) (2016)
- [SFNet: Learning Object-aware Semantic Correspondence](https://mlsanity.com/paper/1904.01810/) (2019)
- [Proposal Flow: Semantic Correspondences from Object Proposals](https://mlsanity.com/paper/1703.07144/) (2017)
- [FCSS: Fully Convolutional Self-Similarity for Dense Semantic Correspondence](https://mlsanity.com/paper/1702.00926/) (2017)
- [REGAL: Representation Learning-based Graph Alignment](https://mlsanity.com/paper/1802.06257/) (2018)
- [Do Convnets Learn Correspondence?](https://mlsanity.com/paper/1411.1091/) (2014)

## Built on by (most cited first, 1 of 1)

- [Automated Camera Calibration via Homography Estimation with GNNs](https://mlsanity.com/paper/2311.02598/) (2023)

## Abstract (arXiv)

Image matching is a key component of many tasks in computer vision and its main objective is to find correspondences between features extracted from different natural images. When images are represented as graphs, image matching boils down to the problem of graph matching which has been studied intensively in the past. In recent years, graph neural networks have shown great potential in the graph matching task, and have also been applied to image matching. In this paper, we propose a graph neural network for the problem of image matching. The proposed method first generates initial soft correspondences between keypoints using localized node embeddings and then iteratively refines the initial correspondences using a series of graph neural network layers. We evaluate our method on natural image datasets with keypoint annotations and show that, in comparison to a state-of-the-art model, our method speeds up inference times without sacrificing prediction accuracy.