All Graphs Lead to Rome: Learning Geometric and Cycle-Consistent Representations with Graph Convolutional Networks

Abstract

Image feature matching is a fundamental part of many geometric computer vision applications, and using multiple images can improve performance. In this work, we formulate multi-image matching as a graph embedding problem then use a Graph Convolutional Network to learn an appropriate embedding function for aligning image features. We use cycle consistency to train our network in an unsupervised fashion, since ground truth correspondence is difficult or expensive to aquire. In addition, geometric consistency losses can be added at training time, even if the information is not available in the test set, unlike previous approaches that optimize cycle consistency directly. To the best of our knowledge, no other works have used learning for multi-image feature matching. Our experiments show that our method is competitive with other optimization based approaches.

9 pages, 7 figures, 2 tables, 2 supplemental figures

References in corpus (8)

• Adam: A Method for Stochastic Optimization
• Semi-Supervised Classification with Graph Convolutional Networks
• Geometric deep learning: going beyond Euclidean data
• Spectral Networks and Locally Connected Networks on Graphs
• Universal Correspondence Network
• Distributed Consistent Data Association
• Multi-Image Semantic Matching by Mining Consistent Features
• Distributable Consistent Multi-Object Matching