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

Jingyi Cao, Bo Liu, Yunqian Wen, Rong Xie, Li Song; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 3334-3342

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.

Related Material


[pdf]
[bibtex]
@InProceedings{Cao_2021_ICCV, author = {Cao, Jingyi and Liu, Bo and Wen, Yunqian and Xie, Rong and Song, Li}, title = {Personalized and Invertible Face De-Identification by Disentangled Identity Information Manipulation}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2021}, pages = {3334-3342} }