The Devil is in the Details: StyleFeatureEditor for Detail-Rich StyleGAN Inversion and High Quality Image Editing
This addresses a key bottleneck in high-quality image editing for applications like digital art and media, representing an incremental improvement over existing methods.
The paper tackles the problem of balancing reconstruction quality and editability in StyleGAN inversion for real image manipulation, introducing StyleFeatureEditor which enables editing in both w-latents and F-latents to preserve finer details, and demonstrates state-of-the-art performance in reconstruction quality and handling out-of-domain examples.
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.