细节决定成败：StyleFeatureEditor 用于细节丰富的 StyleGAN 反演与高质量图像编辑
The Devil is in the Details: StyleFeatureEditor for Detail-Rich StyleGAN Inversion and High Quality Image Editing
AI总结：
针对 StyleGAN 反演中重建细节与编辑能力难以兼顾的问题，提出 StyleFeatureEditor，在 w 与 F 潜在空间联合编辑并配合专用训练流程，实现高质量细节重建、保留及域外图像编辑。
摘要：
通过 StyleGAN 反演来操纵真实图像属性的任务已得到广泛研究。该过程包括：从训练良好的 StyleGAN 生成器中搜索能够合成真实图像的潜在变量，修改这些潜在变量，然后合成具有所需编辑效果的图像。必须在重建质量与编辑能力之间取得平衡。早期研究利用低维 W 空间进行潜在搜索，这有助于有效编辑，但在重建复杂细节方面存在困难。较新的研究转向高维特征空间 F，该空间能够成功反演输入图像，但在编辑过程中会丢失大量细节。本文提出 StyleFeatureEditor——一种可在 w 潜在变量和 F 潜在变量中进行编辑的新方法。该技术不仅能够重建更精细的图像细节，还能确保这些细节在编辑过程中得到保留。我们还提出了一种新的训练流程，专门用于训练模型准确编辑 F 潜在变量。将本文方法与最先进的编码方法进行比较，结果表明我们的模型在重建质量方面表现优异，并且即使对具有挑战性的域外样本也能够进行编辑。代码可在 https://github.com/AIRI-Institute/StyleFeatureEditor 获取。
英文摘要：
The task of manipulating real image attributes through StyleGAN inversion has been extensively researched. This process involves searching latent variables from a well-trained StyleGAN generator that can synthesize a real image, modifying these latent variables, and then synthesizing an image with the desired edits. A balance must be struck between the quality of the reconstruction and the ability to edit. Earlier studies utilized the low-dimensional W-space for latent search, which facilitated effective editing but struggled with reconstructing intricate details. More recent research has turned to the high-dimensional feature space F, which successfully inverses the input image but loses much of the detail during editing. In this paper, we introduce StyleFeatureEditor -- a novel method that enables editing in both w-latents and F-latents. This technique not only allows for the reconstruction of finer image details but also ensures their preservation during editing. We also present a new training pipeline specifically designed to train our model to accurately edit F-latents. Our method is compared with state-of-the-art encoding approaches, demonstrating that our model excels in terms of reconstruction quality and is capable of editing even challenging out-of-domain examples. Code is available at https://github.com/AIRI-Institute/StyleFeatureEditor.
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。
