# EigenGAN: Layer-Wise Eigen-Learning for GANs

arXiv: https://arxiv.org/abs/2104.12476 · HTML: https://mlsanity.com/paper/2104.12476/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 45 references that are in the map.
- First posted on arXiv 26 Apr 2021.

## Builds on (most cited first, 30 of 34)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [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)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Spectral Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/1802.05957/) (2018)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets](https://mlsanity.com/paper/1606.03657/) (2016)
- [Network Dissection: Quantifying Interpretability of Deep Visual Representations](https://mlsanity.com/paper/1704.05796/) (2017)
- [Which Training Methods for GANs do actually Converge?](https://mlsanity.com/paper/1801.04406/) (2018)
- [Wasserstein GAN](https://mlsanity.com/paper/1701.07875/) (2017)
- [GANSpace: Discovering Interpretable GAN Controls](https://mlsanity.com/paper/2004.02546/) (2020)
- [StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks](https://mlsanity.com/paper/1612.03242/) (2016)
- [Conditional Image Synthesis With Auxiliary Classifier GANs](https://mlsanity.com/paper/1610.09585/) (2016)
- [f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization](https://mlsanity.com/paper/1606.00709/) (2016)
- [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)
- [Adversarial Autoencoders](https://mlsanity.com/paper/1511.05644/) (2015)
- [Adversarial Feature Learning](https://mlsanity.com/paper/1605.09782/) (2016)
- [Unsupervised Discovery of Interpretable Directions in the GAN Latent Space](https://mlsanity.com/paper/2002.03754/) (2020)
- [cGANs with Projection Discriminator](https://mlsanity.com/paper/1802.05637/) (2018)
- [Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks](https://mlsanity.com/paper/1506.05751/) (2015)
- [GANalyze: Toward Visual Definitions of Cognitive Image Properties](https://mlsanity.com/paper/1906.10112/) (2019)
- [Object Detectors Emerge in Deep Scene CNNs](https://mlsanity.com/paper/1412.6856/) (2014)
- [Stabilizing Training of Generative Adversarial Networks through Regularization](https://mlsanity.com/paper/1705.09367/) (2017)
- [Semantic Hierarchy Emerges in Deep Generative Representations for Scene Synthesis](https://mlsanity.com/paper/1911.09267/) (2019)
- [Controlling generative models with continuous factors of variations](https://mlsanity.com/paper/2001.10238/) (2020)

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

- [3D-aware Image Synthesis via Learning Structural and Textural Representations](https://mlsanity.com/paper/2112.10759/) (2021)
- [3D Shape Reconstruction from 2D Images with Disentangled Attribute Flow](https://mlsanity.com/paper/2203.15190/) (2022)
- [3D-Aware Semantic-Guided Generative Model for Human Synthesis](https://mlsanity.com/paper/2112.01422/) (2021)
- [User-Controllable Latent Transformer for StyleGAN Image Layout Editing](https://mlsanity.com/paper/2208.12408/) (2022)
- [Region-Based Semantic Factorization in GANs](https://mlsanity.com/paper/2202.09649/) (2022)
- [Controllable and Guided Face Synthesis for Unconstrained Face Recognition](https://mlsanity.com/paper/2207.10180/) (2022)
- [PandA: Unsupervised Learning of Parts and Appearances in the Feature Maps of GANs](https://mlsanity.com/paper/2206.00048/) (2022)
- [Attribute Group Editing for Reliable Few-shot Image Generation](https://mlsanity.com/paper/2203.08422/) (2022)
- [LinkGAN: Linking GAN Latents to Pixels for Controllable Image Synthesis](https://mlsanity.com/paper/2301.04604/) (2023)
- [Hidden Convexity of Wasserstein GANs: Interpretable Generative Models with Closed-Form Solutions](https://mlsanity.com/paper/2107.05680/) (2021)
- [Injecting 3D Perception of Controllable NeRF-GAN into StyleGAN for Editable Portrait Image Synthesis](https://mlsanity.com/paper/2207.10257/) (2022)
- [Masked-Attention Diffusion Guidance for Spatially Controlling Text-to-Image Generation](https://mlsanity.com/paper/2308.06027/) (2023)
- [Collaborative Neural Rendering using Anime Character Sheets](https://mlsanity.com/paper/2207.05378/) (2022)
- [Training and Tuning Generative Neural Radiance Fields for Attribute-Conditional 3D-Aware Face Generation](https://mlsanity.com/paper/2208.12550/) (2022)
- [MM2Latent: Text-to-facial image generation and editing in GANs with multimodal assistance](https://mlsanity.com/paper/2409.11010/) (2024)
- [Stable Attribute Group Editing for Reliable Few-shot Image Generation](https://mlsanity.com/paper/2302.00179/) (2023)
- [Turbo-Sim: a generalised generative model with a physical latent space](https://mlsanity.com/paper/2112.10629/) (2021)
- [PixelFolder: An Efficient Progressive Pixel Synthesis Network for Image Generation](https://mlsanity.com/paper/2204.00833/) (2022)
- [Orthogonal SVD Covariance Conditioning and Latent Disentanglement](https://mlsanity.com/paper/2212.05599/) (2022)
- [Householder Projector for Unsupervised Latent Semantics Discovery](https://mlsanity.com/paper/2307.08012/) (2023)
- [Pursuit of a Discriminative Representation for Multiple Subspaces via Sequential Games](https://mlsanity.com/paper/2206.09120/) (2022)
- [GVDIFF: Grounded Text-to-Video Generation with Diffusion Models](https://mlsanity.com/paper/2407.01921/) (2024)
- [Interpreting Generative Adversarial Networks for Interactive Image Generation](https://mlsanity.com/paper/2108.04896/) (2021)
- [pcaGAN: Improving Posterior-Sampling cGANs via Principal Component Regularization](https://mlsanity.com/paper/2411.00605/) (2024)
- [DGAE: Diffusion-Guided Autoencoder for Efficient Latent Representation Learning](https://mlsanity.com/paper/2506.09644/) (2025)
- [ChildPredictor: A Child Face Prediction Framework with Disentangled Learning](https://mlsanity.com/paper/2204.09962/) (2022)
- [A Survey on Leveraging Pre-trained Generative Adversarial Networks for Image Editing and Restoration](https://mlsanity.com/paper/2207.10309/) (2022)
- [Attribute Controllable Beautiful Caucasian Face Generation by Aesthetics Driven Reinforcement Learning](https://mlsanity.com/paper/2208.04517/) (2022)
- [StyleHumanCLIP: Text-guided Garment Manipulation for StyleGAN-Human](https://mlsanity.com/paper/2305.16759/) (2023)
- [3D Semantic Subspace Traverser: Empowering 3D Generative Model with Shape Editing Capability](https://mlsanity.com/paper/2307.14051/) (2023)

## Abstract (arXiv)

Recent studies on Generative Adversarial Network (GAN) reveal that different layers of a generative CNN hold different semantics of the synthesized images. However, few GAN models have explicit dimensions to control the semantic attributes represented in a specific layer. This paper proposes EigenGAN which is able to unsupervisedly mine interpretable and controllable dimensions from different generator layers. Specifically, EigenGAN embeds one linear subspace with orthogonal basis into each generator layer. Via generative adversarial training to learn a target distribution, these layer-wise subspaces automatically discover a set of "eigen-dimensions" at each layer corresponding to a set of semantic attributes or interpretable variations. By traversing the coefficient of a specific eigen-dimension, the generator can produce samples with continuous changes corresponding to a specific semantic attribute. Taking the human face for example, EigenGAN can discover controllable dimensions for high-level concepts such as pose and gender in the subspace of deep layers, as well as low-level concepts such as hue and color in the subspace of shallow layers. Moreover, in the linear case, we theoretically prove that our algorithm derives the principal components as PCA does. Codes can be found in https://github.com/LynnHo/EigenGAN-Tensorflow.