# Fully-Trainable Deep Matching

arXiv: https://arxiv.org/abs/1609.03532 · HTML: https://mlsanity.com/paper/1609.03532/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Sep 2016.

## Built on by (most cited first, 4 of 4)

- [Learning to Focus: Cascaded Feature Matching Network for Few-shot Image Recognition](https://mlsanity.com/paper/2101.05018/) (2021)
- [Color-aware Deep Temporal Backdrop Duplex Matting System](https://mlsanity.com/paper/2306.02954/) (2023)
- [Using Keypoint Matching and Interactive Self Attention Network to verify Retail POSMs](https://mlsanity.com/paper/2110.03646/) (2021)
- [MicroFlow: Domain-Specific Optical Flow for Ground Deformation Estimation in Seismic Events](https://mlsanity.com/paper/2504.13452/) (2025)

## Abstract (arXiv)

Deep Matching (DM) is a popular high-quality method for quasi-dense image matching. Despite its name, however, the original DM formulation does not yield a deep neural network that can be trained end-to-end via backpropagation. In this paper, we remove this limitation by rewriting the complete DM algorithm as a convolutional neural network. This results in a novel deep architecture for image matching that involves a number of new layer types and that, similar to recent networks for image segmentation, has a U-topology. We demonstrate the utility of the approach by improving the performance of DM by learning it end-to-end on an image matching task.