# SemanticStyleGAN: Learning Compositional Generative Priors for Controllable Image Synthesis and Editing

arXiv: https://arxiv.org/abs/2112.02236 · HTML: https://mlsanity.com/paper/2112.02236/

## Key facts

- Cited by 58 papers in the map (data through 14 Oct 2026).
- Builds on 68 of its 77 references that are in the map.
- First posted on arXiv 4 Dec 2021.

## Builds on (most cited first, 30 of 68)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [Semantic Image Synthesis with Spatially-Adaptive Normalization](https://mlsanity.com/paper/1903.07291/) (2019)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [Alias-Free Generative Adversarial Networks](https://mlsanity.com/paper/2106.12423/) (2021)
- [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](https://mlsanity.com/paper/1711.11585/) (2017)
- [StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery](https://mlsanity.com/paper/2103.17249/) (2021)
- [GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields](https://mlsanity.com/paper/2011.12100/) (2020)
- [Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation](https://mlsanity.com/paper/2008.00951/) (2020)
- [pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis](https://mlsanity.com/paper/2012.00926/) (2020)
- [Interpreting the Latent Space of GANs for Semantic Face Editing](https://mlsanity.com/paper/1907.10786/) (2019)
- [GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis](https://mlsanity.com/paper/2007.02442/) (2020)
- [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)
- [FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models](https://mlsanity.com/paper/1810.01367/) (2018)
- [Designing an Encoder for StyleGAN Image Manipulation](https://mlsanity.com/paper/2102.02766/) (2021)
- [StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesis](https://mlsanity.com/paper/2110.08985/) (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)
- [MONet: Unsupervised Scene Decomposition and Representation](https://mlsanity.com/paper/1901.11390/) (2019)
- [Multi-Object Representation Learning with Iterative Variational Inference](https://mlsanity.com/paper/1903.00450/) (2019)
- [Image2StyleGAN++: How to Edit the Embedded Images?](https://mlsanity.com/paper/1911.11544/) (2019)
- [StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flows](https://mlsanity.com/paper/2008.02401/) (2020)

## Built on by (most cited first, 30 of 58)

- [MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing](https://mlsanity.com/paper/2306.10012/) (2023)
- [HQ-Edit: A High-Quality Dataset for Instruction-based Image Editing](https://mlsanity.com/paper/2404.09990/) (2024)
- [OmniEdit: Building Image Editing Generalist Models Through Specialist Supervision](https://mlsanity.com/paper/2411.07199/) (2024)
- [TALL: Thumbnail Layout for Deepfake Video Detection](https://mlsanity.com/paper/2307.07494/) (2023)
- [Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing](https://mlsanity.com/paper/2504.02826/) (2025)
- [StyleAvatar: Real-time Photo-realistic Portrait Avatar from a Single Video](https://mlsanity.com/paper/2305.00942/) (2023)
- [Controllable 3D Face Synthesis with Conditional Generative Occupancy Fields](https://mlsanity.com/paper/2206.08361/) (2022)
- [OmniAvatar: Geometry-Guided Controllable 3D Head Synthesis](https://mlsanity.com/paper/2303.15539/) (2023)
- [Sem2NeRF: Converting Single-View Semantic Masks to Neural Radiance Fields](https://mlsanity.com/paper/2203.10821/) (2022)
- [Not Only Generative Art: Stable Diffusion for Content-Style Disentanglement in Art Analysis](https://mlsanity.com/paper/2304.10278/) (2023)
- [Latent Traversals in Generative Models as Potential Flows](https://mlsanity.com/paper/2304.12944/) (2023)
- [GAN-based Facial Attribute Manipulation](https://mlsanity.com/paper/2210.12683/) (2022)
- [3D-aware Blending with Generative NeRFs](https://mlsanity.com/paper/2302.06608/) (2023)
- [EmoVOCA: Speech-Driven Emotional 3D Talking Heads](https://mlsanity.com/paper/2403.12886/) (2024)
- [Text-centric Alignment for Multi-Modality Learning](https://mlsanity.com/paper/2402.08086/) (2024)
- [Semantic 3D-aware Portrait Synthesis and Manipulation Based on Compositional Neural Radiance Field](https://mlsanity.com/paper/2302.01579/) (2023)
- [Closed-Loop Unsupervised Representation Disentanglement with β-VAE Distillation and Diffusion Probabilistic Feedback](https://mlsanity.com/paper/2402.02346/) (2024)
- [Training and Tuning Generative Neural Radiance Fields for Attribute-Conditional 3D-Aware Face Generation](https://mlsanity.com/paper/2208.12550/) (2022)
- [Edge Guided GANs with Multi-Scale Contrastive Learning for Semantic Image Synthesis](https://mlsanity.com/paper/2307.12084/) (2023)
- [Double InfoGAN for Contrastive Analysis](https://mlsanity.com/paper/2401.17776/) (2024)
- [PEGASUS: Personalized Generative 3D Avatars with Composable Attributes](https://mlsanity.com/paper/2402.10636/) (2024)
- [HairCUP: Hair Compositional Universal Prior for 3D Gaussian Avatars](https://mlsanity.com/paper/2507.19481/) (2025)
- [ReGANIE: Rectifying GAN Inversion Errors for Accurate Real Image Editing](https://mlsanity.com/paper/2301.13402/) (2023)
- [Zero-shot-Learning Cross-Modality Data Translation Through Mutual Information Guided Stochastic Diffusion](https://mlsanity.com/paper/2301.13743/) (2023)
- [LC-NeRF: Local Controllable Face Generation in Neural Randiance Field](https://mlsanity.com/paper/2302.09486/) (2023)
- [FACEMUG: A Multimodal Generative and Fusion Framework for Local Facial Editing](https://mlsanity.com/paper/2412.19009/) (2024)
- [IDE-3D: Interactive Disentangled Editing for High-Resolution 3D-aware Portrait Synthesis](https://mlsanity.com/paper/2205.15517/) (2022)
- [Extracting Semantic Knowledge from GANs with Unsupervised Learning](https://mlsanity.com/paper/2211.16710/) (2022)
- [LatentSwap3D: Semantic Edits on 3D Image GANs](https://mlsanity.com/paper/2212.01381/) (2022)
- [Householder Projector for Unsupervised Latent Semantics Discovery](https://mlsanity.com/paper/2307.08012/) (2023)

## Abstract (arXiv)

Recent studies have shown that StyleGANs provide promising prior models for downstream tasks on image synthesis and editing. However, since the latent codes of StyleGANs are designed to control global styles, it is hard to achieve a fine-grained control over synthesized images. We present SemanticStyleGAN, where a generator is trained to model local semantic parts separately and synthesizes images in a compositional way. The structure and texture of different local parts are controlled by corresponding latent codes. Experimental results demonstrate that our model provides a strong disentanglement between different spatial areas. When combined with editing methods designed for StyleGANs, it can achieve a more fine-grained control to edit synthesized or real images. The model can also be extended to other domains via transfer learning. Thus, as a generic prior model with built-in disentanglement, it could facilitate the development of GAN-based applications and enable more potential downstream tasks.