Maximum Spatial Perturbation for Image-to-Image Translation (Official Implementation)

This repository is by Yanwu Xu
and contains the PyTorch source code to
reproduce the experiments in our CVPR2022 paper Maximum Spatial Perturbation Consistency for Unpaired Image-to-Image Translation by Yanwu Xu, Shaoan Xie, Wenhao Wu, Kun Zhang, Mingming Gong* and Kayhan Batmanghelich* (* Equal Advising)

Purturbation Consistency Spatial Alignment
0.5 0.5

Face Pose Transfer data can be downloaded here

Experiments on real data

To run the code on the face pose transfer data. 1. download the data from above link 2. unzip the data to the data folder 3. sh run_gcpert.sh

GitHub

View Github

 

 

 

To finish reading, please visit source site