# Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization

arXiv: https://arxiv.org/abs/1703.06868 · HTML: https://mlsanity.com/paper/1703.06868/

## Key facts

- Cited by 2,010 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Mar 2017.

## Built on by (most cited first, 30 of 2010)

- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [LRM: Large Reconstruction Model for Single Image to 3D](https://mlsanity.com/paper/2311.04400/) (2023)
- [Generalizing to Unseen Domains: A Survey on Domain Generalization](https://mlsanity.com/paper/2103.03097/) (2021)
- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields](https://mlsanity.com/paper/2304.06706/) (2023)
- [Domain Generalization with MixStyle](https://mlsanity.com/paper/2104.02008/) (2021)
- [Neural Fields in Visual Computing and Beyond](https://mlsanity.com/paper/2111.11426/) (2021)
- [Tackling the Generative Learning Trilemma with Denoising Diffusion GANs](https://mlsanity.com/paper/2112.07804/) (2021)
- [StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesis](https://mlsanity.com/paper/2110.08985/) (2021)
- [Towards Out-Of-Distribution Generalization: A Survey](https://mlsanity.com/paper/2108.13624/) (2021)
- [MotionCLIP: Exposing Human Motion Generation to CLIP Space](https://mlsanity.com/paper/2203.08063/) (2022)
- [Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Model](https://mlsanity.com/paper/2311.06214/) (2023)
- [GAN Inversion: A Survey](https://mlsanity.com/paper/2101.05278/) (2021)
- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [Text2Mesh: Text-Driven Neural Stylization for Meshes](https://mlsanity.com/paper/2112.03221/) (2021)
- [Geometry-Informed Neural Operator for Large-Scale 3D PDEs](https://mlsanity.com/paper/2309.00583/) (2023)
- [Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning](https://mlsanity.com/paper/2210.08823/) (2022)
- [Inversion-Based Style Transfer with Diffusion Models](https://mlsanity.com/paper/2211.13203/) (2022)
- [VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware Normalization](https://mlsanity.com/paper/2103.16874/) (2021)
- [DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort](https://mlsanity.com/paper/2104.06490/) (2021)
- [Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation](https://mlsanity.com/paper/2306.07954/) (2023)
- [SimSwap: An Efficient Framework For High Fidelity Face Swapping](https://mlsanity.com/paper/2106.06340/) (2021)
- [HINet: Half Instance Normalization Network for Image Restoration](https://mlsanity.com/paper/2105.06086/) (2021)
- [BBDM: Image-to-image Translation with Brownian Bridge Diffusion Models](https://mlsanity.com/paper/2205.07680/) (2022)
- [Large Scale Image Completion via Co-Modulated Generative Adversarial Networks](https://mlsanity.com/paper/2103.10428/) (2021)
- [Style Aligned Image Generation via Shared Attention](https://mlsanity.com/paper/2312.02133/) (2023)
- [More Control for Free! Image Synthesis with Semantic Diffusion Guidance](https://mlsanity.com/paper/2112.05744/) (2021)
- [PIRenderer: Controllable Portrait Image Generation via Semantic Neural Rendering](https://mlsanity.com/paper/2109.08379/) (2021)
- [CLIPstyler: Image Style Transfer with a Single Text Condition](https://mlsanity.com/paper/2112.00374/) (2021)
- [High-Fidelity GAN Inversion for Image Attribute Editing](https://mlsanity.com/paper/2109.06590/) (2021)

## Abstract (arXiv)

Gatys et al. recently introduced a neural algorithm that renders a content image in the style of another image, achieving so-called style transfer. However, their framework requires a slow iterative optimization process, which limits its practical application. Fast approximations with feed-forward neural networks have been proposed to speed up neural style transfer. Unfortunately, the speed improvement comes at a cost: the network is usually tied to a fixed set of styles and cannot adapt to arbitrary new styles. In this paper, we present a simple yet effective approach that for the first time enables arbitrary style transfer in real-time. At the heart of our method is a novel adaptive instance normalization (AdaIN) layer that aligns the mean and variance of the content features with those of the style features. Our method achieves speed comparable to the fastest existing approach, without the restriction to a pre-defined set of styles. In addition, our approach allows flexible user controls such as content-style trade-off, style interpolation, color & spatial controls, all using a single feed-forward neural network.