# E2Style: Improve the Efficiency and Effectiveness of StyleGAN Inversion

arXiv: https://arxiv.org/abs/2104.07661 · HTML: https://mlsanity.com/paper/2104.07661/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 78 references that are in the map.
- First posted on arXiv 15 Apr 2021.

## Builds on (most cited first, 30 of 45)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [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)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Spectral Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/1802.05957/) (2018)
- [LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop](https://mlsanity.com/paper/1506.03365/) (2015)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [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)
- [MaskGAN: Towards Diverse and Interactive Facial Image Manipulation](https://mlsanity.com/paper/1907.11922/) (2019)
- [GANSpace: Discovering Interpretable GAN Controls](https://mlsanity.com/paper/2004.02546/) (2020)
- [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)
- [Closed-Form Factorization of Latent Semantics in GANs](https://mlsanity.com/paper/2007.06600/) (2020)
- [Image2StyleGAN++: How to Edit the Embedded Images?](https://mlsanity.com/paper/1911.11544/) (2019)
- [Lookahead Optimizer: k steps forward, 1 step back](https://mlsanity.com/paper/1907.08610/) (2019)
- [CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition](https://mlsanity.com/paper/2004.00288/) (2020)
- [ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinement](https://mlsanity.com/paper/2104.02699/) (2021)
- [Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation](https://mlsanity.com/paper/2003.13659/) (2020)
- [FaceShifter: Towards High Fidelity And Occlusion Aware Face Swapping](https://mlsanity.com/paper/1912.13457/) (2019)
- [Image Processing Using Multi-Code GAN Prior](https://mlsanity.com/paper/1912.07116/) (2019)

## Built on by (most cited first, 30 of 33)

- [A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?](https://mlsanity.com/paper/2303.11717/) (2023)
- [Schedule Your Edit: A Simple yet Effective Diffusion Noise Schedule for Image Editing](https://mlsanity.com/paper/2410.18756/) (2024)
- [Face Generation and Editing with StyleGAN: A Survey](https://mlsanity.com/paper/2212.09102/) (2022)
- [Boundary Guided Learning-Free Semantic Control with Diffusion Models](https://mlsanity.com/paper/2302.08357/) (2023)
- [Personalized Image Generation with Deep Generative Models: A Decade Survey](https://mlsanity.com/paper/2502.13081/) (2025)
- [StyleInV: A Temporal Style Modulated Inversion Network for Unconditional Video Generation](https://mlsanity.com/paper/2308.16909/) (2023)
- [Intra-Source Style Augmentation for Improved Domain Generalization](https://mlsanity.com/paper/2210.10175/) (2022)
- [HairCLIPv2: Unifying Hair Editing via Proxy Feature Blending](https://mlsanity.com/paper/2310.10651/) (2023)
- [From Posterior Sampling to Meaningful Diversity in Image Restoration](https://mlsanity.com/paper/2310.16047/) (2023)
- [IA-FaceS: A Bidirectional Method for Semantic Face Editing](https://mlsanity.com/paper/2203.13097/) (2022)
- [Intra- & Extra-Source Exemplar-Based Style Synthesis for Improved Domain Generalization](https://mlsanity.com/paper/2307.00648/) (2023)
- [What Decreases Editing Capability? Domain-Specific Hybrid Refinement for Improved GAN Inversion](https://mlsanity.com/paper/2301.12141/) (2023)
- [LSAP: Rethinking Inversion Fidelity, Perception and Editability in GAN Latent Space](https://mlsanity.com/paper/2209.12746/) (2022)
- [3D-GOI: 3D GAN Omni-Inversion for Multifaceted and Multi-object Editing](https://mlsanity.com/paper/2311.12050/) (2023)
- [DNPM: A Neural Parametric Model for the Synthesis of Facial Geometric Details](https://mlsanity.com/paper/2405.19688/) (2024)
- [Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation](https://mlsanity.com/paper/2509.00428/) (2025)
- [GAN Inversion for Image Editing via Unsupervised Domain Adaptation](https://mlsanity.com/paper/2211.12123/) (2022)
- [Out-of-domain GAN inversion via Invertibility Decomposition for Photo-Realistic Human Face Manipulation](https://mlsanity.com/paper/2212.09262/) (2022)
- [High-Resolution GAN Inversion for Degraded Images in Large Diverse Datasets](https://mlsanity.com/paper/2302.03406/) (2023)
- [Text-to-3D Generation by 2D Editing](https://mlsanity.com/paper/2412.05929/) (2024)
- [Improving generative adversarial network inversion via fine-tuning GAN encoders](https://mlsanity.com/paper/2108.10201/) (2021)
- [Diffusion based Zero-shot Medical Image-to-Image Translation for Cross Modality Segmentation](https://mlsanity.com/paper/2404.01102/) (2024)
- [HF-VTON: High-Fidelity Virtual Try-On via Consistent Geometric and Semantic Alignment](https://mlsanity.com/paper/2505.19638/) (2025)
- [A Survey on Leveraging Pre-trained Generative Adversarial Networks for Image Editing and Restoration](https://mlsanity.com/paper/2207.10309/) (2022)
- [StylePrompter: All Styles Need Is Attention](https://mlsanity.com/paper/2307.16151/) (2023)
- [Gradual Residuals Alignment: A Dual-Stream Framework for GAN Inversion and Image Attribute Editing](https://mlsanity.com/paper/2402.14398/) (2024)
- [Hierarchical Semantic Compression for Consistent Image Semantic Restoration](https://mlsanity.com/paper/2502.16799/) (2025)
- [Multivariate Diffusion Transformer with Decoupled Attention for High-Fidelity Mask-Text Collaborative Facial Generation](https://mlsanity.com/paper/2511.12631/) (2025)
- [LatentForensics: Towards frugal deepfake detection in the StyleGAN latent space](https://mlsanity.com/paper/2303.17222/) (2023)
- [A Sampling-Based Domain Generalization Study with Diffusion Generative Models](https://mlsanity.com/paper/2310.09213/) (2023)

## Abstract (arXiv)

This paper studies the problem of StyleGAN inversion, which plays an essential role in enabling the pretrained StyleGAN to be used for real image editing tasks. The goal of StyleGAN inversion is to find the exact latent code of the given image in the latent space of StyleGAN. This problem has a high demand for quality and efficiency. Existing optimization-based methods can produce high-quality results, but the optimization often takes a long time. On the contrary, forward-based methods are usually faster but the quality of their results is inferior. In this paper, we present a new feed-forward network "E2Style" for StyleGAN inversion, with significant improvement in terms of efficiency and effectiveness. In our inversion network, we introduce: 1) a shallower backbone with multiple efficient heads across scales; 2) multi-layer identity loss and multi-layer face parsing loss to the loss function; and 3) multi-stage refinement. Combining these designs together forms an effective and efficient method that exploits all benefits of optimization-based and forward-based methods. Quantitative and qualitative results show that our E2Style performs better than existing forward-based methods and comparably to state-of-the-art optimization-based methods while maintaining the high efficiency as well as forward-based methods. Moreover, a number of real image editing applications demonstrate the efficacy of our E2Style. Our code is available at urlhttps://github.com/wty-ustc/e2style