Survey on leveraging pre-trained generative adversarial networks for image editing and restoration  

作　　者：Ming LIU Yuxiang WEI Xiaohe WU Wangmeng ZUO Lei ZHANG 

机构地区：[1]School of Computer Science and Technology,Harbin Institute of Technology,Harbin 150001,China [2]Department of Computing,Hong Kong Polytechnic University,Hong Kong 999077,China

出　　处：《Science China(Information Sciences)》2023年第5期24-51,共28页中国科学（信息科学）（英文版）

基　　金：supported by National Natural Science Foundation of China(Grant Nos.U19A2073,62006064);Hong Kong RGC RIF(Grant No.R5001-18);2020 Heilongjiang Provincial Natural Science Foundation Joint Guidance Project(Grant No.LH2020C001)。

摘　　要：Generative adversarial networks(GANs)have drawn enormous attention due to their simple yet efective training mechanism and superior image generation quality.With the ability to generate photorealistic high-resolution(e.g.,1024×1024)images,recent GAN models have greatly narrowed the gaps between the generated images and the real ones.Therefore,many recent studies show emerging interest to take advantage of pre-trained GAN models by exploiting the well-disentangled latent space and the learned GAN priors.In this study,we briefly review recent progress on leveraging pre-trained large-scale GAN models from three aspects,i.e.,(1)the training of large-scale generative adversarial networks,(2)exploring and understanding the pre-trained GAN models,and(3)leveraging these models for subsequent tasks like image restoration and editing.

关 键 词：SURVEY generative adversarial networks pre-trained models image editing image restoration 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]