# Near Perfect GAN Inversion

arXiv: https://arxiv.org/abs/2202.11833 · HTML: https://mlsanity.com/paper/2202.11833/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 34 references that are in the map.
- First posted on arXiv 23 Feb 2022.

## Builds on (most cited first, 27 of 27)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [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)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Alias-Free Generative Adversarial Networks](https://mlsanity.com/paper/2106.12423/) (2021)
- [StarGAN v2: Diverse Image Synthesis for Multiple Domains](https://mlsanity.com/paper/1912.01865/) (2019)
- [Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation](https://mlsanity.com/paper/2008.00951/) (2020)
- [Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?](https://mlsanity.com/paper/1904.03189/) (2019)
- [Recognition in Terra Incognita](https://mlsanity.com/paper/1807.04975/) (2018)
- [Closed-Form Factorization of Latent Semantics in GANs](https://mlsanity.com/paper/2007.06600/) (2020)
- [InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs](https://mlsanity.com/paper/2005.09635/) (2020)
- [PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models](https://mlsanity.com/paper/2003.03808/) (2020)
- [Generative Visual Manipulation on the Natural Image Manifold](https://mlsanity.com/paper/1609.03552/) (2016)
- [StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation](https://mlsanity.com/paper/2011.12799/) (2020)
- [ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinement](https://mlsanity.com/paper/2104.02699/) (2021)
- [High-Fidelity GAN Inversion for Image Attribute Editing](https://mlsanity.com/paper/2109.06590/) (2021)
- [Optimizing the Latent Space of Generative Networks](https://mlsanity.com/paper/1707.05776/) (2017)
- [Adversarial Latent Autoencoders](https://mlsanity.com/paper/2004.04467/) (2020)
- [Seeing What a GAN Cannot Generate](https://mlsanity.com/paper/1910.11626/) (2019)
- [Inverting The Generator Of A Generative Adversarial Network](https://mlsanity.com/paper/1611.05644/) (2016)
- [Lessons from Archives: Strategies for Collecting Sociocultural Data in Machine Learning](https://mlsanity.com/paper/1912.10389/) (2019)
- [Using latent space regression to analyze and leverage compositionality in GANs](https://mlsanity.com/paper/2103.10426/) (2021)
- [GAN Inversion for Out-of-Range Images with Geometric Transformations](https://mlsanity.com/paper/2108.08998/) (2021)
- [Ensembling with Deep Generative Views](https://mlsanity.com/paper/2104.14551/) (2021)
- [WarpedGANSpace: Finding non-linear RBF paths in GAN latent space](https://mlsanity.com/paper/2109.13357/) (2021)

## Built on by (most cited first, 15 of 15)

- [Real-Time Radiance Fields for Single-Image Portrait View Synthesis](https://mlsanity.com/paper/2305.02310/) (2023)
- [Diffusion Video Autoencoders: Toward Temporally Consistent Face Video Editing via Disentangled Video Encoding](https://mlsanity.com/paper/2212.02802/) (2022)
- [Personalized Image Generation with Deep Generative Models: A Decade Survey](https://mlsanity.com/paper/2502.13081/) (2025)
- [InvertAvatar: Incremental GAN Inversion for Generalized Head Avatars](https://mlsanity.com/paper/2312.02222/) (2023)
- [DiFaReli++: Diffusion Face Relighting with Consistent Cast Shadows](https://mlsanity.com/paper/2304.09479/) (2023)
- [3D-aware Blending with Generative NeRFs](https://mlsanity.com/paper/2302.06608/) (2023)
- [Synthetic Face Datasets Generation via Latent Space Exploration from Brownian Identity Diffusion](https://mlsanity.com/paper/2405.00228/) (2024)
- [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)
- [JoIN: Joint GANs Inversion for Intrinsic Image Decomposition](https://mlsanity.com/paper/2305.11321/) (2023)
- [Revisiting Latent Space of GAN Inversion for Real Image Editing](https://mlsanity.com/paper/2307.08995/) (2023)
- [A Survey on Leveraging Pre-trained Generative Adversarial Networks for Image Editing and Restoration](https://mlsanity.com/paper/2207.10309/) (2022)
- [Face Verification Bypass](https://mlsanity.com/paper/2203.15068/) (2022)
- [Gradient Adjusting Networks for Domain Inversion](https://mlsanity.com/paper/2302.11413/) (2023)
- [Balancing Reconstruction and Editing Quality of GAN Inversion for Real Image Editing with StyleGAN Prior Latent Space](https://mlsanity.com/paper/2306.00241/) (2023)

## Abstract (arXiv)

To edit a real photo using Generative Adversarial Networks (GANs), we need a GAN inversion algorithm to identify the latent vector that perfectly reproduces it. Unfortunately, whereas existing inversion algorithms can synthesize images similar to real photos, they cannot generate the identical clones needed in most applications. Here, we derive an algorithm that achieves near perfect reconstructions of photos. Rather than relying on encoder- or optimization-based methods to find an inverse mapping on a fixed generator G(·), we derive an approach to locally adjust G(·) to more optimally represent the photos we wish to synthesize. This is done by locally tweaking the learned mapping G(·) s.t. | bf x - G(bf z) |<ε, with bf x the photo we wish to reproduce, bf z the latent vector, |·| an appropriate metric, and ε > 0 a small scalar. We show that this approach can not only produce synthetic images that are indistinguishable from the real photos we wish to replicate, but that these images are readily editable. We demonstrate the effectiveness of the derived algorithm on a variety of datasets including human faces, animals, and cars, and discuss its importance for diversity and inclusion.