PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume

We present a compact but effective CNN model for optical flow, called PWC-Net. PWC-Net has been designed according to simple and well-established principles: pyramidal processing, warping, and the use of a cost volume. Cast in a learnable feature pyramid, PWC-Net uses the current optical flow estima...

Full description

Saved in:
Bibliographic Details
Published in2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition pp. 8934 - 8943
Main Authors Sun, Deqing, Yang, Xiaodong, Liu, Ming-Yu, Kautz, Jan
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2018
Subjects
Adaptive optics
Benchmark testing
Computational modeling
Computer vision
Feature extraction
Optical imaging
Task analysis
Online AccessGet full text

Cover

More Information
Summary:We present a compact but effective CNN model for optical flow, called PWC-Net. PWC-Net has been designed according to simple and well-established principles: pyramidal processing, warping, and the use of a cost volume. Cast in a learnable feature pyramid, PWC-Net uses the current optical flow estimate to warp the CNN features of the second image. It then uses the warped features and features of the first image to construct a cost volume, which is processed by a CNN to estimate the optical flow. PWC-Net is 17 times smaller in size and easier to train than the recent FlowNet2 model. Moreover, it outperforms all published optical flow methods on the MPI Sintel final pass and KITTI 2015 benchmarks, running at about 35 fps on Sintel resolution (1024 Ã- 436) images. Our models are available on our project website.
ISSN:1063-6919
DOI:10.1109/CVPR.2018.00931