Delving deep into pixelized face recovery and defense

• Main Authors: ZHONG, Zhixuan, DU, Yong, ZHOU, Yang, CAO, Jiangzhong, HE, Shengfeng
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2022
• Subjects: Contradictory problems; Data driven; Deterministics; Face depixelization; Face pixelization; Feature representation; Image recovery; Inpainting; Pixelization; Privacy preservation; Databases and Information Systems
• Online Access: https://ink.library.smu.edu.sg/sis_research/8372; https://ink.library.smu.edu.sg/context/sis_research/article/9375/viewcontent/Delving_deep_into_pixelized_face_recovery_and_defense.pdf
• Institution: Singapore Management University

Pixelization is arguably one of the most well-adopted deterministic obfuscation techniques for privacy preservation purposes. Although the recovery of pixelized faces is underexplored, the powerful deep neural networks might combat this problem in a data-driven manner. As a consequence, an unbreakab...