This is the implementation of the paper:
I. Rocco, R. Arandjelović and J. Sivic. Convolutional neural network architecture for geometric matching. CVPR 2017 [website][arXiv]
using the MatConvNet toolbox for MATLAB
- demo.m downloads trained models and shows how to perform alignment
- evaluate.m shows how to evaluate the trained models on the ProposalFlow and Caltech-101 datasets.
- demo_train.m shows how to train a new model