The Devil is in the Details: StyleFeatureEditor for Detail-Rich StyleGAN Inversion and High Quality Image Editing

TL;DR

This paper introduces StyleFeatureEditor, a novel method for high-quality, detail-preserving image editing using StyleGAN inversion that combines editing in both w- and F-latents, improving reconstruction and editing of intricate details.

Contribution

The paper presents a new technique enabling editing in both w- and F-latents, preserving fine details during StyleGAN-based image editing, along with a specialized training pipeline.

Findings

Outperforms state-of-the-art encoding methods in reconstruction quality.

Capable of editing challenging out-of-domain images.

Preserves intricate image details during editing.

Abstract

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.