Copyright (C) 2018 NVIDIA Corporation. All rights reserved. Licensed under the CC BY-NC-SA 4.0 license (https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode).
For Caffe users, please refer to Caffe/README.md.
For PyTorch users, please refer to PyTorch/README.md
The PyTorch implementation almost matches the Caffe implementation (average EPE on the final pass of the Sintel training set: 2.31 by Pytorch and 2.29 by Caffe).
PWC-Net fuses several classic optical flow estimation techniques, including image pyramid, warping, and cost volume, in an end-to-end trainable deep neural networks for achieving state-of-the-art results.
Talk at robust vision challenge workshop
Talk at CVPR 2018 conference (starts ~7:00)
If you use PWC-Net, please cite the following paper:
@InProceedings{Sun2018PWC-Net,
author = {Deqing Sun and Xiaodong Yang and Ming-Yu Liu and Jan Kautz},
title = {{PWC-Net}: {CNNs} for Optical Flow Using Pyramid, Warping, and Cost Volume},
booktitle = CVPR,
year = {2018},
}
or the arXiv paper
@article{sun2017pwc,
author={Sun, Deqing and Yang, Xiaodong and Liu, Ming-Yu and Kautz, Jan},
title={{PWC-Net}: {CNNs} for Optical Flow Using Pyramid, Warping, and Cost Volume},
journal={arXiv preprint arXiv:1709.02371},
year={2017}
}
or the updated and extended version
@article{Sun2018:Model:Training:Flow,
author={Sun, Deqing and Yang, Xiaodong and Liu, Ming-Yu and Kautz, Jan},
title={Models Matter, So Does Training: An Empirical Study of CNNs for Optical Flow Estimation},
journal={arXiv preprint arXiv:1809.05571},
year={2018}
}
Learning Rigidity in Dynamic Scenes with a Moving Camera for 3D Motion Field Estimation (ECCV 2018)
Deqing Sun (deqings@nvidia.com)