IEEE - Institute of Electrical and Electronics Engineers, Inc. - A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation

2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Author(s): Nikolaus Mayer ; Eddy Ilg ; Philip Hausser ; Philipp Fischer ; Daniel Cremers ; Alexey Dosovitskiy ; Thomas Brox
Publisher: IEEE - Institute of Electrical and Electronics Engineers, Inc.
Publication Date: 1 June 2016
Conference Location: Las Vegas, NV, USA
Conference Date: 27 June 2016
Page(s): 4,040 - 4,048
ISBN (Electronic): 978-1-4673-8851-1
ISSN (Electronic): 1063-6919
DOI: 10.1109/CVPR.2016.438
Regular:

Recent work has shown that optical flow estimation can be formulated as a supervised learning task and can be successfully solved with convolutional networks. Training of the so-called FlowNet was... View More

Advertisement