# Diversified Arbitrary Style Transfer via Deep Feature Perturbation

arXiv: https://arxiv.org/abs/1909.08223 · HTML: https://mlsanity.com/paper/1909.08223/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Sep 2019.

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

- [Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfer](https://mlsanity.com/paper/2312.09008/) (2023)
- [StyTr2: Image Style Transfer with Transformers](https://mlsanity.com/paper/2105.14576/) (2021)
- [StyleDiffusion: Controllable Disentangled Style Transfer via Diffusion Models](https://mlsanity.com/paper/2308.07863/) (2023)
- [ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows](https://mlsanity.com/paper/2103.16877/) (2021)
- [Rethinking Style Transfer: From Pixels to Parameterized Brushstrokes](https://mlsanity.com/paper/2103.17185/) (2021)
- [A survey of synthetic data augmentation methods in computer vision](https://mlsanity.com/paper/2403.10075/) (2024)
- [Style-Aware Normalized Loss for Improving Arbitrary Style Transfer](https://mlsanity.com/paper/2104.10064/) (2021)
- [Draw Your Art Dream: Diverse Digital Art Synthesis with Multimodal Guided Diffusion](https://mlsanity.com/paper/2209.13360/) (2022)
- [On the Road to Online Adaptation for Semantic Image Segmentation](https://mlsanity.com/paper/2203.16195/) (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)
- [Fast Differentiable Matrix Square Root and Inverse Square Root](https://mlsanity.com/paper/2201.12543/) (2022)
- [Fast Differentiable Matrix Square Root](https://mlsanity.com/paper/2201.08663/) (2022)
- [S2WAT: Image Style Transfer via Hierarchical Vision Transformer using Strips Window Attention](https://mlsanity.com/paper/2210.12381/) (2022)
- [Texture Reformer: Towards Fast and Universal Interactive Texture Transfer](https://mlsanity.com/paper/2112.02788/) (2021)
- [DivSwapper: Towards Diversified Patch-based Arbitrary Style Transfer](https://mlsanity.com/paper/2101.06381/) (2021)
- [StylerDALLE: Language-Guided Style Transfer Using a Vector-Quantized Tokenizer of a Large-Scale Generative Model](https://mlsanity.com/paper/2303.09268/) (2023)
- [Adversarial Semantic Hallucination for Domain Generalized Semantic Segmentation](https://mlsanity.com/paper/2106.04144/) (2021)
- [Industrial Style Transfer with Large-scale Geometric Warping and Content Preservation](https://mlsanity.com/paper/2203.12835/) (2022)
- [Quality Evaluation of Arbitrary Style Transfer: Subjective Study and Objective Metric](https://mlsanity.com/paper/2208.00623/) (2022)
- [Orthogonal SVD Covariance Conditioning and Latent Disentanglement](https://mlsanity.com/paper/2212.05599/) (2022)
- [Mamba-ST: State Space Model for Efficient Style Transfer](https://mlsanity.com/paper/2409.10385/) (2024)
- [Improving Covariance Conditioning of the SVD Meta-layer by Orthogonality](https://mlsanity.com/paper/2207.02119/) (2022)
- [ArtFusion: Controllable Arbitrary Style Transfer using Dual Conditional Latent Diffusion Models](https://mlsanity.com/paper/2306.09330/) (2023)
- [StyleFlow For Content-Fixed Image to Image Translation](https://mlsanity.com/paper/2207.01909/) (2022)
- [Style Spectroscope: Improve Interpretability and Controllability through Fourier Analysis](https://mlsanity.com/paper/2208.06140/) (2022)
- [SpectralCLIP: Preventing Artifacts in Text-Guided Style Transfer from a Spectral Perspective](https://mlsanity.com/paper/2303.09270/) (2023)
- [DyArtbank: Diverse Artistic Style Transfer via Pre-trained Stable Diffusion and Dynamic Style Prompt Artbank](https://mlsanity.com/paper/2503.08392/) (2025)
- [CAMS: Color-Aware Multi-Style Transfer](https://mlsanity.com/paper/2106.13920/) (2021)
- [Batch-efficient EigenDecomposition for Small and Medium Matrices](https://mlsanity.com/paper/2207.04228/) (2022)

## Abstract (arXiv)

Image style transfer is an underdetermined problem, where a large number of solutions can satisfy the same constraint (the content and style). Although there have been some efforts to improve the diversity of style transfer by introducing an alternative diversity loss, they have restricted generalization, limited diversity and poor scalability. In this paper, we tackle these limitations and propose a simple yet effective method for diversified arbitrary style transfer. The key idea of our method is an operation called deep feature perturbation (DFP), which uses an orthogonal random noise matrix to perturb the deep image feature maps while keeping the original style information unchanged. Our DFP operation can be easily integrated into many existing WCT (whitening and coloring transform)-based methods, and empower them to generate diverse results for arbitrary styles. Experimental results demonstrate that this learning-free and universal method can greatly increase the diversity while maintaining the quality of stylization.