CLKN: Cascaded Lucas-Kanade Networks for Image Alignment

Che-Han Chang, Chun-Nan Chou, Edward Y. Chang; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 2213-2221

Abstract


This paper proposes a data-driven approach for image alignment. Our main contribution is a novel network architecture that combines the strengths of convolutional neural networks (CNNs) and the Lucas-Kanade algorithm. The main component of this architecture is a Lucas-Kanade layer that performs the inverse compositional algorithm on convolutional feature maps. To train our network, we develop a cascaded feature learning method that incorporates the coarse-to-fine strategy into the training process. This method learns a pyramid representation of convolutional features in a cascaded manner and yields a cascaded network that performs coarse-to-fine alignment on the feature pyramids. We apply our model to the task of homography estimation, and perform training and evaluation on a large labeled dataset generated from the MS-COCO dataset. Experimental results show that the proposed approach significantly outperforms the other methods.

Related Material


[pdf] [poster]
[bibtex]
@InProceedings{Chang_2017_CVPR,
author = {Chang, Che-Han and Chou, Chun-Nan and Chang, Edward Y.},
title = {CLKN: Cascaded Lucas-Kanade Networks for Image Alignment},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {July},
year = {2017}
}