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.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyphillips2019all

Related papers

• Learning-based Efficient Graph Similarity Computation Via Multi-scale Convolutional Set Matching (2018)13.60
• Image Retrieval For Structure-from-motion Via Graph Convolutional Network (2020)9.59
• Hierarchical Metric Learning And Matching For 2D And 3D Geometric Correspondences (2018)11.39
• Modeling Text With Graph Convolutional Network For Cross-modal Information Retrieval (2018)11.85
• Multi-scale Convolutions For Learning Context Aware Feature Representations (2019)0.00
• Cross-domain Visual Matching Via Generalized Similarity Measure And Feature Learning (2016)15.54
• Geometric Image Correspondence Verification By Dense Pixel Matching (2019)7.16
• Invgc: Robust Cross-modal Retrieval By Inverse Graph Convolution (2023)3.95