CIAGAN: Conditional Identity Anonymization Generative Adversarial Networks

Maxim Maximov, Ismail Elezi, Laura Leal-Taixe
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
Figure 1: Given a face image, our network anonymizes the face based on the desired identity. In the figure, it can be seen the variability of the generated faces, controlled from a given label. In each triplet, the first image is the real image, while the other two images are different anonymized versions of the real image.
doi:10.1109/cvpr42600.2020.00549 dblp:conf/cvpr/MaximovEL20 fatcat:qy5os5ouozbpvfdlk3dgrkntie