# Demystifying Neural Style Transfer

arXiv: https://arxiv.org/abs/1701.01036 · HTML: https://mlsanity.com/paper/1701.01036/

## Key facts

- Cited by 152 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jan 2017.

## Built on by (most cited first, 30 of 152)

- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [StyleDrop: Text-to-Image Generation in Any Style](https://mlsanity.com/paper/2306.00983/) (2023)
- [StyTr2: Image Style Transfer with Transformers](https://mlsanity.com/paper/2105.14576/) (2021)
- [Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalization](https://mlsanity.com/paper/2203.07740/) (2022)
- [ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows](https://mlsanity.com/paper/2103.16877/) (2021)
- [Stylizing 3D Scene via Implicit Representation and HyperNetwork](https://mlsanity.com/paper/2105.13016/) (2021)
- [Domain Enhanced Arbitrary Image Style Transfer via Contrastive Learning](https://mlsanity.com/paper/2205.09542/) (2022)
- [WildNet: Learning Domain Generalized Semantic Segmentation from the Wild](https://mlsanity.com/paper/2204.01446/) (2022)
- [The "Beatrix'' Resurrections: Robust Backdoor Detection via Gram Matrices](https://mlsanity.com/paper/2209.11715/) (2022)
- [AD-CLIP: Adapting Domains in Prompt Space Using CLIP](https://mlsanity.com/paper/2308.05659/) (2023)
- [Gramian Multimodal Representation Learning and Alignment](https://mlsanity.com/paper/2412.11959/) (2024)
- [ArtFID: Quantitative Evaluation of Neural Style Transfer](https://mlsanity.com/paper/2207.12280/) (2022)
- [Modeling Image Composition for Complex Scene Generation](https://mlsanity.com/paper/2206.00923/) (2022)
- [Rethinking Style Transfer: From Pixels to Parameterized Brushstrokes](https://mlsanity.com/paper/2103.17185/) (2021)
- [Context-Aware Layout to Image Generation with Enhanced Object Appearance](https://mlsanity.com/paper/2103.11897/) (2021)
- [DRB-GAN: A Dynamic ResBlock Generative Adversarial Network for Artistic Style Transfer](https://mlsanity.com/paper/2108.07379/) (2021)
- [StyLIP: Multi-Scale Style-Conditioned Prompt Learning for CLIP-based Domain Generalization](https://mlsanity.com/paper/2302.09251/) (2023)
- [Customizing Text-to-Image Models with a Single Image Pair](https://mlsanity.com/paper/2405.01536/) (2024)
- [Feature-based Style Randomization for Domain Generalization](https://mlsanity.com/paper/2106.03171/) (2021)
- [Do better ImageNet classifiers assess perceptual similarity better?](https://mlsanity.com/paper/2203.04946/) (2022)
- [A survey of synthetic data augmentation methods in computer vision](https://mlsanity.com/paper/2403.10075/) (2024)
- [NeRFFaceEditing: Disentangled Face Editing in Neural Radiance Fields](https://mlsanity.com/paper/2211.07968/) (2022)
- [Attention Distillation: A Unified Approach to Visual Characteristics Transfer](https://mlsanity.com/paper/2502.20235/) (2025)
- [Visualizing Adapted Knowledge in Domain Transfer](https://mlsanity.com/paper/2104.10602/) (2021)
- [FIFO: Learning Fog-invariant Features for Foggy Scene Segmentation](https://mlsanity.com/paper/2204.01587/) (2022)
- [Learning Scene Structure Guidance via Cross-Task Knowledge Transfer for Single Depth Super-Resolution](https://mlsanity.com/paper/2103.12955/) (2021)
- [Style-Aware Normalized Loss for Improving Arbitrary Style Transfer](https://mlsanity.com/paper/2104.10064/) (2021)
- [Aligning Correlation Information for Domain Adaptation in Action Recognition](https://mlsanity.com/paper/2107.04932/) (2021)
- [Learning Graph Neural Networks for Image Style Transfer](https://mlsanity.com/paper/2207.11681/) (2022)
- [DARE-GRAM : Unsupervised Domain Adaptation Regression by Aligning Inverse Gram Matrices](https://mlsanity.com/paper/2303.13325/) (2023)

## Abstract (arXiv)

Neural Style Transfer has recently demonstrated very exciting results which catches eyes in both academia and industry. Despite the amazing results, the principle of neural style transfer, especially why the Gram matrices could represent style remains unclear. In this paper, we propose a novel interpretation of neural style transfer by treating it as a domain adaptation problem. Specifically, we theoretically show that matching the Gram matrices of feature maps is equivalent to minimize the Maximum Mean Discrepancy (MMD) with the second order polynomial kernel. Thus, we argue that the essence of neural style transfer is to match the feature distributions between the style images and the generated images. To further support our standpoint, we experiment with several other distribution alignment methods, and achieve appealing results. We believe this novel interpretation connects these two important research fields, and could enlighten future researches.