PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume
This work addresses optical flow estimation for computer vision applications, offering a more efficient and accurate solution compared to prior methods.
The authors tackled optical flow estimation by proposing PWC-Net, a compact CNN model based on pyramidal processing, warping, and cost volumes, which outperforms all published methods on MPI Sintel and KITTI 2015 benchmarks while being 17 times smaller than FlowNet2 and running at about 35 fps.
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.