DeepPrivacy: A Generative Adversarial Network for Face Anonymization

10 Sep 2019  ·  Håkon Hukkelås, Rudolf Mester, Frank Lindseth ·

We propose a novel architecture which is able to automatically anonymize faces in images while retaining the original data distribution. We ensure total anonymization of all faces in an image by generating images exclusively on privacy-safe information. Our 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, we introduce a diverse dataset of human faces, including unconventional poses, occluded faces, and a vast variability in backgrounds. Finally, we 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 we know, no other solution has been proposed that guarantees the anonymization of faces while generating realistic images.

PDF Abstract

Datasets


Introduced in the Paper:

FDF

Used in the Paper:

FFHQ YFCC100M WIDER FACE

Results from the Paper


 Ranked #1 on Face Anonymization on 2019_test set (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Face Anonymization 2019_test set sm 10% 122 # 1

Methods


No methods listed for this paper. Add relevant methods here