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

TLDR

PWC‑Net is built on the established principles of pyramidal processing, warping, and cost‑volume construction. The authors introduce PWC‑Net, a compact yet effective CNN for estimating optical flow. PWC‑Net employs a learnable feature pyramid, warps second‑image features using the current flow estimate, builds a cost volume with first‑image features, and processes it with a CNN to predict flow. PWC‑Net is 17× smaller and easier to train than FlowNet2, surpasses all published methods on MPI Sintel and KITTI 2015, runs at ~35 fps on Sintel resolution, and its models are publicly available.

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 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.