PatchBatch: A Batch Augmented Loss for Optical Flow

David Gadot, Lior Wolf; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 4236-4245

Abstract


We propose a new pipeline for optical flow computation, based on Deep Learning techniques. We suggest using a Siamese CNN to independently, and in parallel, compute the descriptors of both images. The learned descriptors are then compared efficiently using the L2 norm and do not require network processing of patch pairs. The success of the method is based on an innovative loss function that computes higher moments of the loss distributions for each training batch. Combined with an Approximate Nearest Neighbor patch matching method and a flow interpolation technique, state of the art performance is obtained on the most challenging and competitive optical flow benchmarks.

Related Material


[pdf]
[bibtex]
@InProceedings{Gadot_2016_CVPR,
author = {Gadot, David and Wolf, Lior},
title = {PatchBatch: A Batch Augmented Loss for Optical Flow},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2016}
}