# Rethinking Style Transfer: From Pixels to Parameterized Brushstrokes

arXiv: https://arxiv.org/abs/2103.17185 · HTML: https://mlsanity.com/paper/2103.17185/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 60 references that are in the map.
- First posted on arXiv 31 Mar 2021.

## Builds on (most cited first, 30 of 39)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](https://mlsanity.com/paper/1711.11585/) (2017)
- [StarGAN v2: Diverse Image Synthesis for Multiple Domains](https://mlsanity.com/paper/1912.01865/) (2019)
- [StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation](https://mlsanity.com/paper/1711.09020/) (2017)
- [Multimodal Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1804.04732/) (2018)
- [Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks](https://mlsanity.com/paper/1703.10593/) (2017)
- [Unsupervised Image-to-Image Translation Networks](https://mlsanity.com/paper/1703.00848/) (2017)
- [Universal Style Transfer via Feature Transforms](https://mlsanity.com/paper/1705.08086/) (2017)
- [A Learned Representation For Artistic Style](https://mlsanity.com/paper/1610.07629/) (2016)
- [A Neural Representation of Sketch Drawings](https://mlsanity.com/paper/1704.03477/) (2017)
- [Few-Shot Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1905.01723/) (2019)
- [U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation](https://mlsanity.com/paper/1907.10830/) (2019)
- [Texture Networks: Feed-forward Synthesis of Textures and Stylized Images](https://mlsanity.com/paper/1603.03417/) (2016)
- [Demystifying Neural Style Transfer](https://mlsanity.com/paper/1701.01036/) (2017)
- [A Closed-form Solution to Photorealistic Image Stylization](https://mlsanity.com/paper/1802.06474/) (2018)
- [Synthesizing Programs for Images using Reinforced Adversarial Learning](https://mlsanity.com/paper/1804.01118/) (2018)
- [Learning to Paint With Model-based Deep Reinforcement Learning](https://mlsanity.com/paper/1903.04411/) (2019)
- [Stable and Controllable Neural Texture Synthesis and Style Transfer Using Histogram Losses](https://mlsanity.com/paper/1701.08893/) (2017)
- [A Style-Aware Content Loss for Real-time HD Style Transfer](https://mlsanity.com/paper/1807.10201/) (2018)
- [Collaborative Distillation for Ultra-Resolution Universal Style Transfer](https://mlsanity.com/paper/2003.08436/) (2020)
- [Learning Linear Transformations for Fast Arbitrary Style Transfer](https://mlsanity.com/paper/1808.04537/) (2018)
- [Diversified Arbitrary Style Transfer via Deep Feature Perturbation](https://mlsanity.com/paper/1909.08223/) (2019)
- [Two-Stage Peer-Regularized Feature Recombination for Arbitrary Image Style Transfer](https://mlsanity.com/paper/1906.02913/) (2019)

## Built on by (most cited first, 30 of 42)

- [CLIPstyler: Image Style Transfer with a Single Text Condition](https://mlsanity.com/paper/2112.00374/) (2021)
- [CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoders](https://mlsanity.com/paper/2106.14843/) (2021)
- [StyleDiffusion: Controllable Disentangled Style Transfer via Diffusion Models](https://mlsanity.com/paper/2308.07863/) (2023)
- [StylizedNeRF: Consistent 3D Scene Stylization as Stylized NeRF via 2D-3D Mutual Learning](https://mlsanity.com/paper/2205.12183/) (2022)
- [Paint Transformer: Feed Forward Neural Painting with Stroke Prediction](https://mlsanity.com/paper/2108.03798/) (2021)
- [DiffSketcher: Text Guided Vector Sketch Synthesis through Latent Diffusion Models](https://mlsanity.com/paper/2306.14685/) (2023)
- [ArtFID: Quantitative Evaluation of Neural Style Transfer](https://mlsanity.com/paper/2207.12280/) (2022)
- [CCPL: Contrastive Coherence Preserving Loss for Versatile Style Transfer](https://mlsanity.com/paper/2207.04808/) (2022)
- [ProcessPainter: Learn Painting Process from Sequence Data](https://mlsanity.com/paper/2406.06062/) (2024)
- [MicroAST: Towards Super-Fast Ultra-Resolution Arbitrary Style Transfer](https://mlsanity.com/paper/2211.15313/) (2022)
- [Geometry Transfer for Stylizing Radiance Fields](https://mlsanity.com/paper/2402.00863/) (2024)
- [Stroke-based Neural Painting and Stylization with Dynamically Predicted Painting Region](https://mlsanity.com/paper/2309.03504/) (2023)
- [Facial-Sketch Synthesis: A New Challenge](https://mlsanity.com/paper/2112.15439/) (2021)
- [Region-aware Knowledge Distillation for Efficient Image-to-Image Translation](https://mlsanity.com/paper/2205.12451/) (2022)
- [Industrial Style Transfer with Large-scale Geometric Warping and Content Preservation](https://mlsanity.com/paper/2203.12835/) (2022)
- [Im2Oil: Stroke-Based Oil Painting Rendering with Linearly Controllable Fineness Via Adaptive Sampling](https://mlsanity.com/paper/2209.13219/) (2022)
- [VectorPainter: Advanced Stylized Vector Graphics Synthesis Using Stroke-Style Priors](https://mlsanity.com/paper/2405.02962/) (2024)
- [Intelli-Paint: Towards Developing Human-like Painting Agents](https://mlsanity.com/paper/2112.08930/) (2021)
- [Paint2Pix: Interactive Painting based Progressive Image Synthesis and Editing](https://mlsanity.com/paper/2208.08092/) (2022)
- [Inverse Painting: Reconstructing The Painting Process](https://mlsanity.com/paper/2409.20556/) (2024)
- [WISE: Whitebox Image Stylization by Example-based Learning](https://mlsanity.com/paper/2207.14606/) (2022)
- [SCFlow: Implicitly Learning Style and Content Disentanglement with Flow Models](https://mlsanity.com/paper/2508.03402/) (2025)
- [Interactive Cartoonization with Controllable Perceptual Factors](https://mlsanity.com/paper/2212.09555/) (2022)
- [Stroke-based Rendering: From Heuristics to Deep Learning](https://mlsanity.com/paper/2302.00595/) (2022)
- [Multimodality-guided Image Style Transfer using Cross-modal GAN Inversion](https://mlsanity.com/paper/2312.01671/) (2023)
- [ITstyler: Image-optimized Text-based Style Transfer](https://mlsanity.com/paper/2301.10916/) (2023)
- [Computational Approaches for Traditional Chinese Painting: From the "Six Principles of Painting" Perspective](https://mlsanity.com/paper/2307.14227/) (2023)
- [D2Styler: Advancing Arbitrary Style Transfer with Discrete Diffusion Methods](https://mlsanity.com/paper/2408.03558/) (2024)
- [WaSt-3D: Wasserstein-2 Distance for Scene-to-Scene Stylization on 3D Gaussians](https://mlsanity.com/paper/2409.17917/) (2024)
- [CAMS: Color-Aware Multi-Style Transfer](https://mlsanity.com/paper/2106.13920/) (2021)

## Abstract (arXiv)

There have been many successful implementations of neural style transfer in recent years. In most of these works, the stylization process is confined to the pixel domain. However, we argue that this representation is unnatural because paintings usually consist of brushstrokes rather than pixels. We propose a method to stylize images by optimizing parameterized brushstrokes instead of pixels and further introduce a simple differentiable rendering mechanism. Our approach significantly improves visual quality and enables additional control over the stylization process such as controlling the flow of brushstrokes through user input. We provide qualitative and quantitative evaluations that show the efficacy of the proposed parameterized representation.