Fully-Trainable Deep Matching

Understand

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.