DeepPrivacy: A Generative Adversarial Network for Face Anonymization
By Håkon Hukkelås, Rudolf Mester, Frank Lindseth. International Symposium on Visual Computing, 2019
330 citations recorded by the source corpus.
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.
Subfields: Computer Vision and Pattern Recognition, Law
View Paper: https://www.semanticscholar.org/paper/21c3a96db50863ce3db703df385bf24159497842
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- L. Leal-Taix'e
- Maxim Maximov
- Daniel Gillblad
- Olof Mogren
- Ismail Elezi
- John Martinsson
- Edvin Listo Zec
- Luc Van Gool
Citations in the corpus
- CIAGAN: Conditional Identity Anonymization Generative Adversarial Networks (2020, background): “The faces generated by [14] are still, in general, identifiable by humans.”
- Adversarial representation learning for synthetic replacement of private attributes (2020, background): “Some work assumes access to a privacy-preserving mechanism, such as bounding boxes for faces, and studies how to hide people’s identity by blur-ring (Oh et al., 2016a), removing (Orekondy et al., 2018) or generating the face of other people (Hukkelås et al., 2019) in their place.”