Editing out-of-domain GAN inversion via differential activations

• Main Authors: SONG, Haorui, DU, Yong, XIANG, Tianyi, DONG, Junyu, QIN, Jing, HE, Shengfeng
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2022
• Subjects: Image reconstruction; Semantics; Artificial Intelligence and Robotics
• Online Access: https://ink.library.smu.edu.sg/sis_research/8426; https://ink.library.smu.edu.sg/context/sis_research/article/9429/viewcontent/2207.08134.pdf
• Institution: Singapore Management University

Despite the demonstrated editing capacity in the latent space of a pretrained GAN model, inverting real-world images is stuck in a dilemma that the reconstruction cannot be faithful to the original input. The main reason for this is that the distributions between training and real-world data are mis...