通过残差扭曲实现基于StyleGAN的图像编辑
Warping the Residuals for Image Editing with StyleGAN
AI总结：
针对现有StyleGAN图像逆映射方法难以兼顾保真度与编辑质量的问题，提出含流估计模块的新型逆映射架构，通过扭曲高维潜在特征适配编辑，实现高保真高质量图像编辑，性能优于现有最优方法。
摘要：
StyleGAN模型凭借其具备语义可解释性的潜在空间结构拥有编辑能力，但要编辑真实图像需要成功的GAN逆映射方法。目前已有诸多研究致力于将图像逆映射到StyleGAN的潜在空间中，但这些方法的结果要么对输入图像的保真度较低，要么编辑质量不佳，尤其是在需要大幅变换的编辑任务中。原因在于低维度潜在空间虽提供了可编辑空间，却因信息瓶颈丢失了大量图像细节；而高维度潜在空间能将所有图像细节传递给StyleGAN以实现完美重建，但存在编辑质量低的问题。本文提出一种新型图像逆映射架构，该架构提取高维度潜在特征，并包含一个流估计模块用于扭曲这些特征以适配编辑需求。流是根据编辑后与未编辑潜在编码对应的StyleGAN特征估计得到的。通过估计高维度特征并对其进行扭曲以适配编辑，我们同时实现了对输入图像的高保真度和高质量编辑。我们开展了大量实验，将所提方法与当前最优的逆映射方法进行对比，定性指标与可视化比较均显示出显著提升。
英文摘要：
StyleGAN models show editing capabilities via their semantically interpretable latent organizations which require successful GAN inversion methods to edit real images. Many works have been proposed for inverting images into StyleGAN's latent space. However, their results either suffer from low fidelity to the input image or poor editing qualities, especially for edits that require large transformations. That is because low-rate latent spaces lose many image details due to the information bottleneck even though it provides an editable space. On the other hand, higher-rate latent spaces can pass all the image details to StyleGAN for perfect reconstruction of images but suffer from low editing qualities. In this work, we present a novel image inversion architecture that extracts high-rate latent features and includes a flow estimation module to warp these features to adapt them to edits. The flows are estimated from StyleGAN features of edited and unedited latent codes. By estimating the high-rate features and warping them for edits, we achieve both high-fidelity to the input image and high-quality edits. We run extensive experiments and compare our method with state-of-the-art inversion methods. Qualitative metrics and visual comparisons show significant improvements.
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。
