This study presents anchor-regularized generative adversarial network(GAN)priors to delicately explore the inherent knowledge of a pretrained generative model.Previous research leveraged the latent space of a pretrain...This study presents anchor-regularized generative adversarial network(GAN)priors to delicately explore the inherent knowledge of a pretrained generative model.Previous research leveraged the latent space of a pretrained GAN model to provide a variety of image-editing operations.However,the semantically meaningful regions within latent space are distinctly bounded;therefore,the manipulation of the latent code can easily land out of the domain.To address this problem,we introduce an anchoring mechanism that enables novel and robust image editing.The key insights driving the method are that latent space is structurally organized,and that natural coherence allows semantically correlated latent code to be located in the areas surrounding a meaningful anchor.By using different input anchors,the proposed method forms the basis for a variety of robust and flexible editing operations,including misaligned domain translation,interactive editing,and few-shot interpretable direction exploration.Extensive experiments demonstrated the superior performance of the proposed method compared with state-of-the-art editing methods.展开更多
基金supported by the National Natural Science Foundation of China(No.61972162)Guangdong Natural Science Foundation(No.2021A1515012625)+1 种基金Guangdong Natural Science Funds for Distinguished Young Scholars(No.2023B1515020097)Singapore Ministry of Education Academic Research Fund Tier 1(No.MSS23C002).
文摘This study presents anchor-regularized generative adversarial network(GAN)priors to delicately explore the inherent knowledge of a pretrained generative model.Previous research leveraged the latent space of a pretrained GAN model to provide a variety of image-editing operations.However,the semantically meaningful regions within latent space are distinctly bounded;therefore,the manipulation of the latent code can easily land out of the domain.To address this problem,we introduce an anchoring mechanism that enables novel and robust image editing.The key insights driving the method are that latent space is structurally organized,and that natural coherence allows semantically correlated latent code to be located in the areas surrounding a meaningful anchor.By using different input anchors,the proposed method forms the basis for a variety of robust and flexible editing operations,including misaligned domain translation,interactive editing,and few-shot interpretable direction exploration.Extensive experiments demonstrated the superior performance of the proposed method compared with state-of-the-art editing methods.
