The paper proposes a novel architecture which is able to automatically anonymize faces in images while retaining the original data distribution. Authors ensure total anonymization of all faces in an image by generating images exclusively on privacy-safe information.
The model is based on a conditional generative adversarial network, generating images considering the original pose and image background. The conditional information enables us to generate highly realistic faces with a seamless transition between the generated face and the existing background. Furthermore, the authors introduce a diverse dataset of human faces, including unconventional poses, occluded faces, and a vast variability in backgrounds. Finally, the authors present experimental results reflecting the capability of our model to anonymize images while preserving the data distribution, making the data suitable for further training of deep learning models. As far as the authors know, no other solution has been proposed that guarantees the anonymization of faces while generating realistic images.
See more HERERelated posts: