Personalized and Invertible Face De-Identification by Disentangled Identity Information Manipulation

Abstract

The popularization of intelligent devices including smartphones and surveillance cameras results in more serious privacy issues. De-identification is regarded as an effective tool for visual privacy protection with the process of concealing or replacing identity information. Most of the existing de-identification methods suffer from some limitations since they mainly focus on the protection process and are usually non-reversible. In this paper, we propose a personalized and invertible de-identification method based on the deep generative model, where the main idea is introducing a user-specific password and an adjustable parameter to control the direction and degree of identity variation. Extensive experiments demonstrate the effectiveness and generalization of our proposed framework for both face de-identification and recovery.

Cite

Text

Cao et al. "Personalized and Invertible Face De-Identification by Disentangled Identity Information Manipulation." International Conference on Computer Vision, 2021. doi:10.1109/ICCV48922.2021.00332

Markdown

[Cao et al. "Personalized and Invertible Face De-Identification by Disentangled Identity Information Manipulation." International Conference on Computer Vision, 2021.](https://mlanthology.org/iccv/2021/cao2021iccv-personalized/) doi:10.1109/ICCV48922.2021.00332

BibTeX

@inproceedings{cao2021iccv-personalized,
  title     = {{Personalized and Invertible Face De-Identification by Disentangled Identity Information Manipulation}},
  author    = {Cao, Jingyi and Liu, Bo and Wen, Yunqian and Xie, Rong and Song, Li},
  booktitle = {International Conference on Computer Vision},
  year      = {2021},
  pages     = {3334-3342},
  doi       = {10.1109/ICCV48922.2021.00332},
  url       = {https://mlanthology.org/iccv/2021/cao2021iccv-personalized/}
}