Image Keypoint Matching using Graph Neural Networks
This work addresses image matching for computer vision applications, but it is incremental as it builds on existing graph neural network approaches.
The paper tackles the problem of image keypoint matching by proposing a graph neural network that generates initial soft correspondences and iteratively refines them, resulting in faster inference times without loss of accuracy compared to a state-of-the-art model.
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.