# Style and Content Disentanglement in Generative Adversarial Networks

arXiv: https://arxiv.org/abs/1811.05621 · HTML: https://mlsanity.com/paper/1811.05621/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Nov 2018.

## Built on by (most cited first, 29 of 29)

- [EditGAN: High-Precision Semantic Image Editing](https://mlsanity.com/paper/2111.03186/) (2021)
- [StyleDiffusion: Controllable Disentangled Style Transfer via Diffusion Models](https://mlsanity.com/paper/2308.07863/) (2023)
- [Diagonal Attention and Style-based GAN for Content-Style Disentanglement in Image Generation and Translation](https://mlsanity.com/paper/2103.16146/) (2021)
- [StyleFusion: A Generative Model for Disentangling Spatial Segments](https://mlsanity.com/paper/2107.07437/) (2021)
- [Where and What? Examining Interpretable Disentangled Representations](https://mlsanity.com/paper/2104.05622/) (2021)
- [CF-Font: Content Fusion for Few-shot Font Generation](https://mlsanity.com/paper/2303.14017/) (2023)
- [S2R-DepthNet: Learning a Generalizable Depth-specific Structural Representation](https://mlsanity.com/paper/2104.00877/) (2021)
- [Creativity and Machine Learning: A Survey](https://mlsanity.com/paper/2104.02726/) (2021)
- [Learning disentangled representations via product manifold projection](https://mlsanity.com/paper/2103.01638/) (2021)
- [Not Only Generative Art: Stable Diffusion for Content-Style Disentanglement in Art Analysis](https://mlsanity.com/paper/2304.10278/) (2023)
- [Style Equalization: Unsupervised Learning of Controllable Generative Sequence Models](https://mlsanity.com/paper/2110.02891/) (2021)
- [Double InfoGAN for Contrastive Analysis](https://mlsanity.com/paper/2401.17776/) (2024)
- [U Can't Gen This? A Survey of Intellectual Property Protection Methods for Data in Generative AI](https://mlsanity.com/paper/2406.15386/) (2024)
- [Scalable Font Reconstruction with Dual Latent Manifolds](https://mlsanity.com/paper/2109.06627/) (2021)
- [AE-NeRF: Auto-Encoding Neural Radiance Fields for 3D-Aware Object Manipulation](https://mlsanity.com/paper/2204.13426/) (2022)
- [α-TCVAE: On the relationship between Disentanglement and Diversity](https://mlsanity.com/paper/2411.00588/) (2024)
- [Polymorphic-GAN: Generating Aligned Samples across Multiple Domains with Learned Morph Maps](https://mlsanity.com/paper/2206.02903/) (2022)
- [Towards General Game Representations: Decomposing Games Pixels into Content and Style](https://mlsanity.com/paper/2307.11141/) (2023)
- [Multi-task manifold learning for small sample size datasets](https://mlsanity.com/paper/2111.11655/) (2021)
- [The Cow of Rembrandt - Analyzing Artistic Prompt Interpretation in Text-to-Image Models](https://mlsanity.com/paper/2507.23313/) (2025)
- [Disentangled Representation Learning via Flow Matching](https://mlsanity.com/paper/2602.05214/) (2026)
- [Contextualizing Variation in Text Style Transfer Datasets](https://mlsanity.com/paper/2108.07871/) (2021)
- [Unsupervised Structure-Consistent Image-to-Image Translation](https://mlsanity.com/paper/2208.11546/) (2022)
- [S2-Flow: Joint Semantic and Style Editing of Facial Images](https://mlsanity.com/paper/2211.12209/) (2022)
- [Intelligent Generation of Graphical Game Assets: A Conceptual Framework and Systematic Review of the State of the Art](https://mlsanity.com/paper/2311.10129/) (2023)
- [DISC-GAN: Disentangling Style and Content for Cluster-Specific Synthetic Underwater Image Generation](https://mlsanity.com/paper/2510.10782/) (2025)
- [Rethinking the editing of generative adversarial networks: a method to estimate editing vectors based on dimension reduction](https://mlsanity.com/paper/2305.09454/) (2023)
- [SEER-ZSL: Semantic Encoder-Enhanced Representations for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2312.13100/) (2023)
- [Rethinking Disentanglement under Dependent Factors of Variation](https://mlsanity.com/paper/2408.07016/) (2024)

## Abstract (arXiv)

Disentangling factors of variation within data has become a very challenging problem for image generation tasks. Current frameworks for training a Generative Adversarial Network (GAN), learn to disentangle the representations of the data in an unsupervised fashion and capture the most significant factors of the data variations. However, these approaches ignore the principle of content and style disentanglement in image generation, which means their learned latent code may alter the content and style of the generated images at the same time. This paper describes the Style and Content Disentangled GAN (SC-GAN), a new unsupervised algorithm for training GANs that learns disentangled style and content representations of the data. We assume that the representation of an image can be decomposed into a content code that represents the geometrical information of the data, and a style code that captures textural properties. Consequently, by fixing the style portion of the latent representation, we can generate diverse images in a particular style. Reversely, we can set the content code and generate a specific scene in a variety of styles. The proposed SC-GAN has two components: a content code which is the input to the generator, and a style code which modifies the scene style through modification of the Adaptive Instance Normalization (AdaIN) layers' parameters. We evaluate the proposed SC-GAN framework on a set of baseline datasets.