SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2207.08134 · ECCV · 2022

Editing Out-of-domain GAN Inversion via Differential Activations

Junyu Dong, Haorui Song, Jing Qin, Shengfeng He, Yong Du, Tianyi Xiang

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Despite the demonstrated editing capacity in the latent space of a pretrained GAN model, inverting real-world images is stuck in a dilemma that the reconstruction cannot be faithful to the original input. The main reason for this is that the distributions between training and real-world data are misaligned, and because of that, it is unstable of GAN inversion for real image editing. In this paper, we propose a novel GAN prior based editing framework to tackle the out-of-domain inversion problem with a composition-decomposition paradigm. In particular, during the phase of composition, we introduce a differential activation module for detecting semantic changes from a global perspective, i.e., the relative gap between the features of edited and unedited images. With the aid of the generated Diff-CAM mask, a coarse reconstruction can intuitively be composited by the paired original and edited images. In this way, the attribute-irrelevant regions can be survived in almost whole, while the quality of such an intermediate result is still limited by an unavoidable ghosting effect. Consequently, in the decomposition phase, we further present a GAN prior based deghosting network for separating the final fine edited image from the coarse reconstruction. Extensive experiments exhibit superiorities over the state-of-the-art methods, in terms of qualitative and quantitative evaluations. The robustness and flexibility of our method is also validated on both scenarios of single attribute and multi-attribute manipulations. Code is available at https://github.com/HaoruiSong622/Editing-Out-of-Domain.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2207.08134")
get_code_for_paper("2207.08134")
have("2207.08134")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2207.08134.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2207.08134.svg)](https://syntology.ai/paper/2207.08134)

Connect an agent — have() is free.