# GAN Inversion for Image Editing via Unsupervised Domain Adaptation

arXiv: https://arxiv.org/abs/2211.12123 · HTML: https://mlsanity.com/paper/2211.12123/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 34 references that are in the map.
- First posted on arXiv 22 Nov 2022.

## Builds on (most cited first, 24 of 24)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [On the Variance of the Adaptive Learning Rate and Beyond](https://mlsanity.com/paper/1908.03265/) (2019)
- [Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation](https://mlsanity.com/paper/2008.00951/) (2020)
- [Interpreting the Latent Space of GANs for Semantic Face Editing](https://mlsanity.com/paper/1907.10786/) (2019)
- [Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?](https://mlsanity.com/paper/1904.03189/) (2019)
- [GANSpace: Discovering Interpretable GAN Controls](https://mlsanity.com/paper/2004.02546/) (2020)
- [In-Domain GAN Inversion for Real Image Editing](https://mlsanity.com/paper/2004.00049/) (2020)
- [GAN Inversion: A Survey](https://mlsanity.com/paper/2101.05278/) (2021)
- [Lookahead Optimizer: k steps forward, 1 step back](https://mlsanity.com/paper/1907.08610/) (2019)
- [StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation](https://mlsanity.com/paper/2011.12799/) (2020)
- [CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition](https://mlsanity.com/paper/2004.00288/) (2020)
- [Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation](https://mlsanity.com/paper/2003.13659/) (2020)
- [GAN Prior Embedded Network for Blind Face Restoration in the Wild](https://mlsanity.com/paper/2105.06070/) (2021)
- [High-Fidelity GAN Inversion for Image Attribute Editing](https://mlsanity.com/paper/2109.06590/) (2021)
- [Image Processing Using Multi-Code GAN Prior](https://mlsanity.com/paper/1912.07116/) (2019)
- [Blind Face Restoration via Deep Multi-scale Component Dictionaries](https://mlsanity.com/paper/2008.00418/) (2020)
- [GAN Inversion for Out-of-Range Images with Geometric Transformations](https://mlsanity.com/paper/2108.08998/) (2021)
- [f-Domain-Adversarial Learning: Theory and Algorithms](https://mlsanity.com/paper/2106.11344/) (2021)
- [Style Transformer for Image Inversion and Editing](https://mlsanity.com/paper/2203.07932/) (2022)
- [E2Style: Improve the Efficiency and Effectiveness of StyleGAN Inversion](https://mlsanity.com/paper/2104.07661/) (2021)
- [The f-Divergence Reinforcement Learning Framework](https://mlsanity.com/paper/2109.11867/) (2021)

## Built on by (most cited first, 3 of 3)

- [Real-World Image Variation by Aligning Diffusion Inversion Chain](https://mlsanity.com/paper/2305.18729/) (2023)
- [Generative Prompt Model for Weakly Supervised Object Localization](https://mlsanity.com/paper/2307.09756/) (2023)
- [Prediction of Transportation Index for Urban Patterns in Small and Medium-sized Indian Cities using Hybrid RidgeGAN Model](https://mlsanity.com/paper/2306.05951/) (2023)

## Abstract (arXiv)

Existing GAN inversion methods work brilliantly in reconstructing high-quality (HQ) images while struggling with more common low-quality (LQ) inputs in practical application. To address this issue, we propose Unsupervised Domain Adaptation (UDA) in the inversion process, namely UDA-inversion, for effective inversion and editing of both HQ and LQ images. Regarding unpaired HQ images as the source domain and LQ images as the unlabeled target domain, we introduce a theoretical guarantee: loss value in the target domain is upper-bounded by loss in the source domain and a novel discrepancy function measuring the difference between two domains. Following that, we can only minimize this upper bound to obtain accurate latent codes for HQ and LQ images. Thus, constructive representations of HQ images can be spontaneously learned and transformed into LQ images without supervision. UDA-Inversion achieves a better PSNR of 22.14 on FFHQ dataset and performs comparably to supervised methods.