Demo Code and Network Weights for MPWC-Net++

This is the demo code and network weights for

MPWC-Net++: Evolution of Optical Flow Pyramidal Convolutional Neural Network for Ultrasound Elastography [1]

MPWC-Net++ is a modification of MPWC-Net [2]. It is a pytorch implementation based on pwc-net-irr [3]. To use this code, you need to install pwc-net-irr from:

https://github.com/visinf/irr

Follow the installation process. Replace the pwc_modules.py and pwcnet_irr.py of the original implementation with the files given here.

The following results are expected from the demo code.

If you use this code, please cite the following papers:

[1] Tehrani AK, Rivaz H. MPWC-Net++: Evolution of Optical Flow Pyramidal Convolutional Neural Network for Ultrasound Elastography. SPIE 2021

[2] Tehrani AK, Rivaz H. Displacement estimation in ultrasound elastography using pyramidal convolutional neural network. IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control. 2020 Feb 10.

[2] Hur J, Roth S. Iterative residual refinement for joint optical flow and occlusion estimation. InProceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2019 (pp. 5754-5763).

Should you have any question, contact alikafaei1991@gmail.com