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

arXiv: https://arxiv.org/abs/1901.02078 · HTML: https://mlsanity.com/paper/1901.02078/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jan 2019.

## Built on by (most cited first, 3 of 3)

- [Graph Neural Networks for Cross-Camera Data Association](https://mlsanity.com/paper/2201.06311/) (2022)
- [Distributed Global Structure-from-Motion with a Deep Front-End](https://mlsanity.com/paper/2311.18801/) (2023)
- [Graph Convolutional Network for Multi-Target Multi-Camera Vehicle Tracking](https://mlsanity.com/paper/2211.15538/) (2022)

## Abstract (arXiv)

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.