# Fast Patch-based Style Transfer of Arbitrary Style

arXiv: https://arxiv.org/abs/1612.04337 · HTML: https://mlsanity.com/paper/1612.04337/

## Key facts

- Cited by 92 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Dec 2016.

## Built on by (most cited first, 30 of 92)

- [BBDM: Image-to-image Translation with Brownian Bridge Diffusion Models](https://mlsanity.com/paper/2205.07680/) (2022)
- [AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer](https://mlsanity.com/paper/2108.03647/) (2021)
- [StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators](https://mlsanity.com/paper/2108.00946/) (2021)
- [ARF: Artistic Radiance Fields](https://mlsanity.com/paper/2206.06360/) (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)
- [Generalize then Adapt: Source-Free Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2108.11249/) (2021)
- [A Comprehensive Survey on Segment Anything Model for Vision and Beyond](https://mlsanity.com/paper/2305.08196/) (2023)
- [UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models](https://mlsanity.com/paper/2402.11846/) (2024)
- [CCPL: Contrastive Coherence Preserving Loss for Versatile Style Transfer](https://mlsanity.com/paper/2207.04808/) (2022)
- [3D Photo Stylization: Learning to Generate Stylized Novel Views from a Single Image](https://mlsanity.com/paper/2112.00169/) (2021)
- [Drafting and Revision: Laplacian Pyramid Network for Fast High-Quality Artistic Style Transfer](https://mlsanity.com/paper/2104.05376/) (2021)
- [Domain-Aware Universal Style Transfer](https://mlsanity.com/paper/2108.04441/) (2021)
- [Federated Domain Generalization for Image Recognition via Cross-Client Style Transfer](https://mlsanity.com/paper/2210.00912/) (2022)
- [Customizing Text-to-Image Models with a Single Image Pair](https://mlsanity.com/paper/2405.01536/) (2024)
- [Ref-NPR: Reference-Based Non-Photorealistic Radiance Fields for Controllable Scene Stylization](https://mlsanity.com/paper/2212.02766/) (2022)
- [Dual-Camera Super-Resolution with Aligned Attention Modules](https://mlsanity.com/paper/2109.01349/) (2021)
- [AesPA-Net: Aesthetic Pattern-Aware Style Transfer Networks](https://mlsanity.com/paper/2307.09724/) (2023)
- [Style-Aware Normalized Loss for Improving Arbitrary Style Transfer](https://mlsanity.com/paper/2104.10064/) (2021)
- [PhotoWCT2: Compact Autoencoder for Photorealistic Style Transfer Resulting from Blockwise Training and Skip Connections of High-Frequency Residuals](https://mlsanity.com/paper/2110.11995/) (2021)
- [Learning Graph Neural Networks for Image Style Transfer](https://mlsanity.com/paper/2207.11681/) (2022)
- [In the light of feature distributions: moment matching for Neural Style Transfer](https://mlsanity.com/paper/2103.07208/) (2021)
- [Neural Neighbor Style Transfer](https://mlsanity.com/paper/2203.13215/) (2022)
- [StylizedGS: Controllable Stylization for 3D Gaussian Splatting](https://mlsanity.com/paper/2404.05220/) (2024)
- [AesUST: Towards Aesthetic-Enhanced Universal Style Transfer](https://mlsanity.com/paper/2208.13016/) (2022)
- [ZiGAN: Fine-grained Chinese Calligraphy Font Generation via a Few-shot Style Transfer Approach](https://mlsanity.com/paper/2108.03596/) (2021)
- [SGSST: Scaling Gaussian Splatting StyleTransfer](https://mlsanity.com/paper/2412.03371/) (2024)
- [QuantArt: Quantizing Image Style Transfer Towards High Visual Fidelity](https://mlsanity.com/paper/2212.10431/) (2022)
- [Any-to-Any Style Transfer: Making Picasso and Da Vinci Collaborate](https://mlsanity.com/paper/2304.09728/) (2023)
- [All-to-key Attention for Arbitrary Style Transfer](https://mlsanity.com/paper/2212.04105/) (2022)

## Abstract (arXiv)

Artistic style transfer is an image synthesis problem where the content of an image is reproduced with the style of another. Recent works show that a visually appealing style transfer can be achieved by using the hidden activations of a pretrained convolutional neural network. However, existing methods either apply (i) an optimization procedure that works for any style image but is very expensive, or (ii) an efficient feedforward network that only allows a limited number of trained styles. In this work we propose a simpler optimization objective based on local matching that combines the content structure and style textures in a single layer of the pretrained network. We show that our objective has desirable properties such as a simpler optimization landscape, intuitive parameter tuning, and consistent frame-by-frame performance on video. Furthermore, we use 80,000 natural images and 80,000 paintings to train an inverse network that approximates the result of the optimization. This results in a procedure for artistic style transfer that is efficient but also allows arbitrary content and style images.