# Improving Inversion and Generation Diversity in StyleGAN using a Gaussianized Latent Space

arXiv: https://arxiv.org/abs/2009.06529 · HTML: https://mlsanity.com/paper/2009.06529/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Sep 2020.

## Built on by (most cited first, 30 of 34)

- [Designing an Encoder for StyleGAN Image Manipulation](https://mlsanity.com/paper/2102.02766/) (2021)
- [Zero-shot Image-to-Image Translation](https://mlsanity.com/paper/2302.03027/) (2023)
- [Scaling up GANs for Text-to-Image Synthesis](https://mlsanity.com/paper/2303.05511/) (2023)
- [InfinityGAN: Towards Infinite-Pixel Image Synthesis](https://mlsanity.com/paper/2104.03963/) (2021)
- [Using latent space regression to analyze and leverage compositionality in GANs](https://mlsanity.com/paper/2103.10426/) (2021)
- [In&Out : Diverse Image Outpainting via GAN Inversion](https://mlsanity.com/paper/2104.00675/) (2021)
- [Ensembling with Deep Generative Views](https://mlsanity.com/paper/2104.14551/) (2021)
- [Spatially-Adaptive Multilayer Selection for GAN Inversion and Editing](https://mlsanity.com/paper/2206.08357/) (2022)
- [BlobGAN: Spatially Disentangled Scene Representations](https://mlsanity.com/paper/2205.02837/) (2022)
- [State-of-the-Art in the Architecture, Methods and Applications of StyleGAN](https://mlsanity.com/paper/2202.14020/) (2022)
- [Prior Image-Constrained Reconstruction using Style-Based Generative Models](https://mlsanity.com/paper/2102.12525/) (2021)
- [Deep Saliency Prior for Reducing Visual Distraction](https://mlsanity.com/paper/2109.01980/) (2021)
- [Retrieve in Style: Unsupervised Facial Feature Transfer and Retrieval](https://mlsanity.com/paper/2107.06256/) (2021)
- [StyleGAN of All Trades: Image Manipulation with Only Pretrained StyleGAN](https://mlsanity.com/paper/2111.01619/) (2021)
- [AVA: Inconspicuous Attribute Variation-based Adversarial Attack bypassing DeepFake Detection](https://mlsanity.com/paper/2312.08675/) (2023)
- [FerretNet: Efficient Synthetic Image Detection via Local Pixel Dependencies](https://mlsanity.com/paper/2509.20890/) (2025)
- [PhenDiff: Revealing Subtle Phenotypes with Diffusion Models in Real Images](https://mlsanity.com/paper/2312.08290/) (2023)
- [AgileAvatar: Stylized 3D Avatar Creation via Cascaded Domain Bridging](https://mlsanity.com/paper/2211.07818/) (2022)
- [What's in a Decade? Transforming Faces Through Time](https://mlsanity.com/paper/2210.06642/) (2022)
- [InvGAN: Invertible GANs](https://mlsanity.com/paper/2112.04598/) (2021)
- [FreeStyleGAN: Free-view Editable Portrait Rendering with the Camera Manifold](https://mlsanity.com/paper/2109.09378/) (2021)
- [Progressive Text-to-Image Diffusion with Soft Latent Direction](https://mlsanity.com/paper/2309.09466/) (2023)
- [NatADiff: Adversarial Boundary Guidance for Natural Adversarial Diffusion](https://mlsanity.com/paper/2505.20934/) (2025)
- [LatentKeypointGAN: Controlling Images via Latent Keypoints](https://mlsanity.com/paper/2103.15812/) (2021)
- [Overparameterization Improves StyleGAN Inversion](https://mlsanity.com/paper/2205.06304/) (2022)
- [Ambiguous Annotations: When is a Pedestrian not a Pedestrian?](https://mlsanity.com/paper/2405.08794/) (2024)
- [Differentiable Gaussianization Layers for Inverse Problems Regularized by Deep Generative Models](https://mlsanity.com/paper/2112.03860/) (2021)
- [Mining the manifolds of deep generative models for multiple data-consistent solutions of ill-posed tomographic imaging problems](https://mlsanity.com/paper/2202.05311/) (2022)
- [Prior image-based medical image reconstruction using a style-based generative adversarial network](https://mlsanity.com/paper/2202.08936/) (2022)
- [Revisiting Latent Space of GAN Inversion for Real Image Editing](https://mlsanity.com/paper/2307.08995/) (2023)

## Abstract (arXiv)

Modern Generative Adversarial Networks are capable of creating artificial, photorealistic images from latent vectors living in a low-dimensional learned latent space. It has been shown that a wide range of images can be projected into this space, including images outside of the domain that the generator was trained on. However, while in this case the generator reproduces the pixels and textures of the images, the reconstructed latent vectors are unstable and small perturbations result in significant image distortions. In this work, we propose to explicitly model the data distribution in latent space. We show that, under a simple nonlinear operation, the data distribution can be modeled as Gaussian and therefore expressed using sufficient statistics. This yields a simple Gaussian prior, which we use to regularize the projection of images into the latent space. The resulting projections lie in smoother and better behaved regions of the latent space, as shown using interpolation performance for both real and generated images. Furthermore, the Gaussian model of the distribution in latent space allows us to investigate the origins of artifacts in the generator output, and provides a method for reducing these artifacts while maintaining diversity of the generated images.