# SEAN: Image Synthesis with Semantic Region-Adaptive Normalization

arXiv: https://arxiv.org/abs/1911.12861 · HTML: https://mlsanity.com/paper/1911.12861/

## Key facts

- Cited by 253 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Nov 2019.

## Built on by (most cited first, 30 of 253)

- [SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://mlsanity.com/paper/2108.01073/) (2021)
- [DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation](https://mlsanity.com/paper/2110.02711/) (2021)
- [ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2108.02938/) (2021)
- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [GAN Inversion: A Survey](https://mlsanity.com/paper/2101.05278/) (2021)
- [VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware Normalization](https://mlsanity.com/paper/2103.16874/) (2021)
- [EGSDE: Unpaired Image-to-Image Translation via Energy-Guided Stochastic Differential Equations](https://mlsanity.com/paper/2207.06635/) (2022)
- [Dense Text-to-Image Generation with Attention Modulation](https://mlsanity.com/paper/2308.12964/) (2023)
- [EditGAN: High-Precision Semantic Image Editing](https://mlsanity.com/paper/2111.03186/) (2021)
- [Semantic Image Synthesis via Diffusion Models](https://mlsanity.com/paper/2207.00050/) (2022)
- [Generative Adversarial Transformers](https://mlsanity.com/paper/2103.01209/) (2021)
- [Image-to-Image Translation: Methods and Applications](https://mlsanity.com/paper/2101.08629/) (2021)
- [One-Step Image Translation with Text-to-Image Models](https://mlsanity.com/paper/2403.12036/) (2024)
- [FENeRF: Face Editing in Neural Radiance Fields](https://mlsanity.com/paper/2111.15490/) (2021)
- [Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing](https://mlsanity.com/paper/2104.14754/) (2021)
- [HairCLIP: Design Your Hair by Text and Reference Image](https://mlsanity.com/paper/2112.05142/) (2021)
- [Enhancing Photorealism Enhancement](https://mlsanity.com/paper/2105.04619/) (2021)
- [Aligning Latent and Image Spaces to Connect the Unconnectable](https://mlsanity.com/paper/2104.06954/) (2021)
- [Fine-Grained Face Swapping via Regional GAN Inversion](https://mlsanity.com/paper/2211.14068/) (2022)
- [Freestyle Layout-to-Image Synthesis](https://mlsanity.com/paper/2303.14412/) (2023)
- [PISE: Person Image Synthesis and Editing with Decoupled GAN](https://mlsanity.com/paper/2103.04023/) (2021)
- [Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Images](https://mlsanity.com/paper/2106.07873/) (2021)
- [SemanticStyleGAN: Learning Compositional Generative Priors for Controllable Image Synthesis and Editing](https://mlsanity.com/paper/2112.02236/) (2021)
- [Multimodal Image Synthesis and Editing: The Generative AI Era](https://mlsanity.com/paper/2112.13592/) (2021)
- [OpenForensics: Large-Scale Challenging Dataset For Multi-Face Forgery Detection And Segmentation In-The-Wild](https://mlsanity.com/paper/2107.14480/) (2021)
- [Diverse Semantic Image Synthesis via Probability Distribution Modeling](https://mlsanity.com/paper/2103.06878/) (2021)
- [StyleAlign: Analysis and Applications of Aligned StyleGAN Models](https://mlsanity.com/paper/2110.11323/) (2021)
- [Synthetic Datasets for Autonomous Driving: A Survey](https://mlsanity.com/paper/2304.12205/) (2023)
- [Image Synthesis via Semantic Composition](https://mlsanity.com/paper/2109.07053/) (2021)
- [Region-Aware Face Swapping](https://mlsanity.com/paper/2203.04564/) (2022)

## Abstract (arXiv)

We propose semantic region-adaptive normalization (SEAN), a simple but effective building block for Generative Adversarial Networks conditioned on segmentation masks that describe the semantic regions in the desired output image. Using SEAN normalization, we can build a network architecture that can control the style of each semantic region individually, e.g., we can specify one style reference image per region. SEAN is better suited to encode, transfer, and synthesize style than the best previous method in terms of reconstruction quality, variability, and visual quality. We evaluate SEAN on multiple datasets and report better quantitative metrics (e.g. FID, PSNR) than the current state of the art. SEAN also pushes the frontier of interactive image editing. We can interactively edit images by changing segmentation masks or the style for any given region. We can also interpolate styles from two reference images per region.