# Dynamic Instance Normalization for Arbitrary Style Transfer

arXiv: https://arxiv.org/abs/1911.06953 · HTML: https://mlsanity.com/paper/1911.06953/

## Key facts

- Cited by 83 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Nov 2019.

## Built on by (most cited first, 30 of 83)

- [AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer](https://mlsanity.com/paper/2108.03647/) (2021)
- [StyleDiffusion: Controllable Disentangled Style Transfer via Diffusion Models](https://mlsanity.com/paper/2308.07863/) (2023)
- [Zero-Shot Video Editing Using Off-The-Shelf Image Diffusion Models](https://mlsanity.com/paper/2303.17599/) (2023)
- [Dataset Distillation via Factorization](https://mlsanity.com/paper/2210.16774/) (2022)
- [ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows](https://mlsanity.com/paper/2103.16877/) (2021)
- [Domain Enhanced Arbitrary Image Style Transfer via Contrastive Learning](https://mlsanity.com/paper/2205.09542/) (2022)
- [CCPL: Contrastive Coherence Preserving Loss for Versatile Style Transfer](https://mlsanity.com/paper/2207.04808/) (2022)
- [Vision Transformer with Quadrangle Attention](https://mlsanity.com/paper/2303.15105/) (2023)
- [VSA: Learning Varied-Size Window Attention in Vision Transformers](https://mlsanity.com/paper/2204.08446/) (2022)
- [DRB-GAN: A Dynamic ResBlock Generative Adversarial Network for Artistic Style Transfer](https://mlsanity.com/paper/2108.07379/) (2021)
- [Evaluation and Improvement of Interpretability for Self-Explainable Part-Prototype Networks](https://mlsanity.com/paper/2212.05946/) (2022)
- [Meta Discovery: Learning to Discover Novel Classes given Very Limited Data](https://mlsanity.com/paper/2102.04002/) (2021)
- [General Image-to-Image Translation with One-Shot Image Guidance](https://mlsanity.com/paper/2307.14352/) (2023)
- [Style-Aware Normalized Loss for Improving Arbitrary Style Transfer](https://mlsanity.com/paper/2104.10064/) (2021)
- [Learning with Recoverable Forgetting](https://mlsanity.com/paper/2207.08224/) (2022)
- [Learning Graph Neural Networks for Image Style Transfer](https://mlsanity.com/paper/2207.11681/) (2022)
- [Attention Diversification for Domain Generalization](https://mlsanity.com/paper/2210.04206/) (2022)
- [Task-driven Image Fusion with Learnable Fusion Loss](https://mlsanity.com/paper/2412.03240/) (2024)
- [DynaST: Dynamic Sparse Transformer for Exemplar-Guided Image Generation](https://mlsanity.com/paper/2207.06124/) (2022)
- [AesUST: Towards Aesthetic-Enhanced Universal Style Transfer](https://mlsanity.com/paper/2208.13016/) (2022)
- [MicroAST: Towards Super-Fast Ultra-Resolution Arbitrary Style Transfer](https://mlsanity.com/paper/2211.15313/) (2022)
- [TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptation](https://mlsanity.com/paper/2106.06326/) (2021)
- [Any-to-Any Style Transfer: Making Picasso and Da Vinci Collaborate](https://mlsanity.com/paper/2304.09728/) (2023)
- [InstaStyle: Inversion Noise of a Stylized Image is Secretly a Style Adviser](https://mlsanity.com/paper/2311.15040/) (2023)
- [All-to-key Attention for Arbitrary Style Transfer](https://mlsanity.com/paper/2212.04105/) (2022)
- [Towards Ultra-Resolution Neural Style Transfer via Thumbnail Instance Normalization](https://mlsanity.com/paper/2103.11784/) (2021)
- [S2WAT: Image Style Transfer via Hierarchical Vision Transformer using Strips Window Attention](https://mlsanity.com/paper/2210.12381/) (2022)
- [Consistent Style Transfer](https://mlsanity.com/paper/2201.02233/) (2022)
- [Texture Reformer: Towards Fast and Universal Interactive Texture Transfer](https://mlsanity.com/paper/2112.02788/) (2021)
- [Hierarchical Dynamic Image Harmonization](https://mlsanity.com/paper/2211.08639/) (2022)

## Abstract (arXiv)

Prior normalization methods rely on affine transformations to produce arbitrary image style transfers, of which the parameters are computed in a pre-defined way. Such manually-defined nature eventually results in the high-cost and shared encoders for both style and content encoding, making style transfer systems cumbersome to be deployed in resource-constrained environments like on the mobile-terminal side. In this paper, we propose a new and generalized normalization module, termed as Dynamic Instance Normalization (DIN), that allows for flexible and more efficient arbitrary style transfers. Comprising an instance normalization and a dynamic convolution, DIN encodes a style image into learnable convolution parameters, upon which the content image is stylized. Unlike conventional methods that use shared complex encoders to encode content and style, the proposed DIN introduces a sophisticated style encoder, yet comes with a compact and lightweight content encoder for fast inference. Experimental results demonstrate that the proposed approach yields very encouraging results on challenging style patterns and, to our best knowledge, for the first time enables an arbitrary style transfer using MobileNet-based lightweight architecture, leading to a reduction factor of more than twenty in computational cost as compared to existing approaches. Furthermore, the proposed DIN provides flexible support for state-of-the-art convolutional operations, and thus triggers novel functionalities, such as uniform-stroke placement for non-natural images and automatic spatial-stroke control.