Submitted by Aljaz Bozic.

Submission data

Full namePWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume
DescriptionWe 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 cur- rent 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 (1024x436) images.
Publication titlePWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume
Publication authorsDeqing Sun, Xiaodong Yang, Ming-Yu Liu, Jan Kautz
Publication venueCVPR 2018
Publication URLhttps://arxiv.org/pdf/1709.02371
Input Data TypesUses Depth Input
Programming language(s)Python
HardwareGeForce 1080Ti
Websitehttps://research.nvidia.com/publication/2018-02_PWC-Net%3A-CNNs-for
Source code or download URLhttps://github.com/NVlabs/PWC-Net
Submission creation date17 Mar, 2020
Last edited17 Mar, 2020

Optical Flow

Method InfoAccuracy (<20px)EPE (pixel)
PWC-Netcopyleft0.74822.674