A3GAN: Attribute-aware anonymization networks for face de-identification

• Main Authors: ZHAI, Liming, GUO, Qing, XIE, Xiaofei, MA, Lei, WANG, Yi Estelle, LIU, Yang
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2022
• Subjects: Face de-identification; Facial attribute; Controllability; Artificial Intelligence and Robotics; OS and Networks
• Online Access: https://ink.library.smu.edu.sg/sis_research/7495; https://ink.library.smu.edu.sg/context/sis_research/article/8498/viewcontent/3503161.3547757.pdf
• Institution: Singapore Management University

Face de-identification (De-ID) removes face identity information in face images to avoid personal privacy leakage. Existing face De-ID breaks the raw identity by cutting out the face regions and recovering the corrupted regions via deep generators, which inevitably affect the generation quality and...