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

CVPR 2018  ·  Deqing Sun, Xiaodong Yang, Ming-Yu Liu, Jan Kautz ·

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.

PDF Abstract CVPR 2018 PDF CVPR 2018 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Dense Pixel Correspondence Estimation HPatches PWC-Net Viewpoint I AEPE 4.43 # 3
Viewpoint II AEPE 11.44 # 4
Viewpoint III AEPE 15.47 # 4
Viewpoint IV AEPE 20.17 # 4
Viewpoint V AEPE 28.30 # 4
Optical Flow Estimation KITTI 2015 (train) PWC-Net F1-all 33.7 # 17
EPE 10.35 # 14
Optical Flow Estimation Spring PWCNet 1px total 82.265 # 10

Methods


No methods listed for this paper. Add relevant methods here