From continuity to editability: Inverting GANs with consecutive images

• Main Authors: XU, Yangyang, DU, Yong, XIAO, Wenpeng, XU, Xuemiao, HE, Shengfeng
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2021
• Subjects: Consecutive images; High-fidelity; Image editing; Inversion methods; Inversion process; Joint inversion; Property; Real images; State-of-the-art methods; Video frame; Databases and Information Systems
• Online Access: https://ink.library.smu.edu.sg/sis_research/8528; https://ink.library.smu.edu.sg/context/sis_research/article/9531/viewcontent/From_Continuity_to_Editability__Inverting_GANs_With_Consecutive_Images.pdf
• Institution: Singapore Management University

Existing GAN inversion methods are stuck in a paradox that the inverted codes can either achieve high-fidelity reconstruction, or retain the editing capability. Having only one of them clearly cannot realize real image editing. In this paper, we resolve this paradox by introducing consecutive images...