# Editing Out-of-domain GAN Inversion via Differential Activations

arXiv: https://arxiv.org/abs/2207.08134 · HTML: https://mlsanity.com/paper/2207.08134/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 45 references that are in the map.
- First posted on arXiv 17 Jul 2022.

## Builds on (most cited first, 30 of 35)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation](https://mlsanity.com/paper/1711.09020/) (2017)
- [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)
- [Designing an Encoder for StyleGAN Image Manipulation](https://mlsanity.com/paper/2102.02766/) (2021)
- [In-Domain GAN Inversion for Real Image Editing](https://mlsanity.com/paper/2004.00049/) (2020)
- [InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs](https://mlsanity.com/paper/2005.09635/) (2020)
- [Image2StyleGAN++: How to Edit the Embedded Images?](https://mlsanity.com/paper/1911.11544/) (2019)
- [StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flows](https://mlsanity.com/paper/2008.02401/) (2020)
- [Generative Visual Manipulation on the Natural Image Manifold](https://mlsanity.com/paper/1609.03552/) (2016)
- [Learning to Discover Cross-Domain Relations with Generative Adversarial Networks](https://mlsanity.com/paper/1703.05192/) (2017)
- [ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinement](https://mlsanity.com/paper/2104.02699/) (2021)
- [AttGAN: Facial Attribute Editing by Only Changing What You Want](https://mlsanity.com/paper/1711.10678/) (2017)
- [GAN Prior Embedded Network for Blind Face Restoration in the Wild](https://mlsanity.com/paper/2105.06070/) (2021)
- [Image Processing Using Multi-Code GAN Prior](https://mlsanity.com/paper/1912.07116/) (2019)
- [Editing in Style: Uncovering the Local Semantics of GANs](https://mlsanity.com/paper/2004.14367/) (2020)
- [STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing](https://mlsanity.com/paper/1904.09709/) (2019)
- [Attention Branch Network: Learning of Attention Mechanism for Visual Explanation](https://mlsanity.com/paper/1812.10025/) (2018)
- [Generative Hierarchical Features from Synthesizing Images](https://mlsanity.com/paper/2007.10379/) (2020)
- [StyleGAN2 Distillation for Feed-forward Image Manipulation](https://mlsanity.com/paper/2003.03581/) (2020)
- [Collaborative Learning for Faster StyleGAN Embedding](https://mlsanity.com/paper/2007.01758/) (2020)

## Built on by (most cited first, 14 of 14)

- [Drag Your Noise: Interactive Point-based Editing via Diffusion Semantic Propagation](https://mlsanity.com/paper/2404.01050/) (2024)
- [D4-VTON: Dynamic Semantics Disentangling for Differential Diffusion based Virtual Try-On](https://mlsanity.com/paper/2407.15111/) (2024)
- [RIGID: Recurrent GAN Inversion and Editing of Real Face Videos](https://mlsanity.com/paper/2308.06097/) (2023)
- [Expanding Expressiveness of Diffusion Models with Limited Data via Self-Distillation based Fine-Tuning](https://mlsanity.com/paper/2311.01018/) (2023)
- [Make It So: Steering StyleGAN for Any Image Inversion and Editing](https://mlsanity.com/paper/2304.14403/) (2023)
- [OmniVTON: Training-Free Universal Virtual Try-On](https://mlsanity.com/paper/2507.15037/) (2025)
- [Intra- & Extra-Source Exemplar-Based Style Synthesis for Improved Domain Generalization](https://mlsanity.com/paper/2307.00648/) (2023)
- [NaRCan: Natural Refined Canonical Image with Integration of Diffusion Prior for Video Editing](https://mlsanity.com/paper/2406.06523/) (2024)
- [Out-of-domain GAN inversion via Invertibility Decomposition for Photo-Realistic Human Face Manipulation](https://mlsanity.com/paper/2212.09262/) (2022)
- [Partial-View Object View Synthesis via Filtered Inversion](https://mlsanity.com/paper/2304.00673/) (2023)
- [iFADIT: Invertible Face Anonymization via Disentangled Identity Transform](https://mlsanity.com/paper/2501.04390/) (2025)
- [CoLoR-GAN: Continual Few-Shot Learning with Low-Rank Adaptation in Generative Adversarial Networks](https://mlsanity.com/paper/2510.13869/) (2025)
- [ZIGNeRF: Zero-shot 3D Scene Representation with Invertible Generative Neural Radiance Fields](https://mlsanity.com/paper/2306.02741/) (2023)
- [OmniVTON++: Training-Free Universal Virtual Try-On with Principal Pose Guidance](https://mlsanity.com/paper/2602.14552/) (2026)

## Abstract (arXiv)

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, ie, 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.