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

TL;DR

PWC-Net is a compact CNN model for optical flow that uses pyramidal processing, warping, and cost volume, achieving state-of-the-art accuracy with significantly fewer parameters and real-time performance.

Contribution

The paper introduces PWC-Net, a novel CNN architecture for optical flow that is smaller, easier to train, and more accurate than previous models like FlowNet2.

Findings

Outperforms all published optical flow methods on MPI Sintel and KITTI 2015 benchmarks.

17 times smaller in size than FlowNet2.

Operates at about 35 fps on high-resolution images.

Abstract

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 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. Our models are available on https://github.com/NVlabs/PWC-Net.