基于无监督域适应的图像编辑GAN反演
GAN Inversion for Image Editing via Unsupervised Domain Adaptation
AI总结：
针对现有GAN反演方法难以处理低质量图像的问题，提出基于无监督域适应的UDA-inversion方法，通过最小化目标域损失上界实现高低质量图像的有效反演与编辑，在FFHQ数据集上PSNR达22.14。
摘要：
现有GAN反演方法在重建高质量（HQ）图像方面表现出色，但在实际应用中处理更常见的低质量（LQ）输入时却面临困难。为解决此问题，我们在反演过程中提出无监督域适应（UDA），即UDA-inversion，以实现对HQ和LQ图像的有效反演与编辑。将未配对的HQ图像视为源域，LQ图像视为无标签目标域，我们引入了一个理论保证：目标域的损失值以源域损失和一个衡量两域差异的新型差异函数为上界。据此，我们只需最小化该上界即可获得HQ和LQ图像的准确潜码。从而，HQ图像的构造性表示可被自发学习并无监督地转化为LQ图像。UDA-Inversion在FFHQ数据集上实现了22.14的更佳PSNR，且表现与监督方法相当。
英文摘要：
Existing GAN inversion methods work brilliantly in reconstructing high-quality (HQ) images while struggling with more common low-quality (LQ) inputs in practical application. To address this issue, we propose Unsupervised Domain Adaptation (UDA) in the inversion process, namely UDA-inversion, for effective inversion and editing of both HQ and LQ images. Regarding unpaired HQ images as the source domain and LQ images as the unlabeled target domain, we introduce a theoretical guarantee: loss value in the target domain is upper-bounded by loss in the source domain and a novel discrepancy function measuring the difference between two domains. Following that, we can only minimize this upper bound to obtain accurate latent codes for HQ and LQ images. Thus, constructive representations of HQ images can be spontaneously learned and transformed into LQ images without supervision. UDA-Inversion achieves a better PSNR of 22.14 on FFHQ dataset and performs comparably to supervised methods.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
