# StyleStegan: Leak-free Style Transfer Based on Feature Steganography

arXiv: https://arxiv.org/abs/2307.00225 · HTML: https://mlsanity.com/paper/2307.00225/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 36 references that are in the map.
- First posted on arXiv 1 Jul 2023.

## Builds on (most cited first, 22 of 22)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Density estimation using Real NVP](https://mlsanity.com/paper/1605.08803/) (2016)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Glow: Generative Flow with Invertible 1x1 Convolutions](https://mlsanity.com/paper/1807.03039/) (2018)
- [NICE: Non-linear Independent Components Estimation](https://mlsanity.com/paper/1410.8516/) (2014)
- [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)
- [CLIPstyler: Image Style Transfer with a Single Text Condition](https://mlsanity.com/paper/2112.00374/) (2021)
- [Texture Networks: Feed-forward Synthesis of Textures and Stylized Images](https://mlsanity.com/paper/1603.03417/) (2016)
- [Visual Attribute Transfer through Deep Image Analogy](https://mlsanity.com/paper/1705.01088/) (2017)
- [Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalization](https://mlsanity.com/paper/2203.07740/) (2022)
- [Avatar-Net: Multi-scale Zero-shot Style Transfer by Feature Decoration](https://mlsanity.com/paper/1805.03857/) (2018)
- [Domain Enhanced Arbitrary Image Style Transfer via Contrastive Learning](https://mlsanity.com/paper/2205.09542/) (2022)
- [Arbitrary Style Transfer with Deep Feature Reshuffle](https://mlsanity.com/paper/1805.04103/) (2018)
- [Cycle-Consistent Inverse GAN for Text-to-Image Synthesis](https://mlsanity.com/paper/2108.01361/) (2021)
- [AesUST: Towards Aesthetic-Enhanced Universal Style Transfer](https://mlsanity.com/paper/2208.13016/) (2022)
- [Towards Ultra-Resolution Neural Style Transfer via Thumbnail Instance Normalization](https://mlsanity.com/paper/2103.11784/) (2021)
- [Name Your Style: An Arbitrary Artist-aware Image Style Transfer](https://mlsanity.com/paper/2202.13562/) (2022)
- [Self-Contained Stylization via Steganography for Reverse and Serial Style Transfer](https://mlsanity.com/paper/1812.03910/) (2018)
- [Parameter-Free Style Projection for Arbitrary Style Transfer](https://mlsanity.com/paper/2003.07694/) (2020)
- [Face Destylization](https://mlsanity.com/paper/1802.01237/) (2018)

## Abstract (arXiv)

In modern social networks, existing style transfer methods suffer from a serious content leakage issue, which hampers the ability to achieve serial and reversible stylization, thereby hindering the further propagation of stylized images in social networks. To address this problem, we propose a leak-free style transfer method based on feature steganography. Our method consists of two main components: a style transfer method that accomplishes artistic stylization on the original image and an image steganography method that embeds content feature secrets on the stylized image. The main contributions of our work are as follows: 1) We identify and explain the phenomenon of content leakage and its underlying causes, which arise from content inconsistencies between the original image and its subsequent stylized image. 2) We design a neural flow model for achieving loss-free and biased-free style transfer. 3) We introduce steganography to hide content feature information on the stylized image and control the subsequent usage rights. 4) We conduct comprehensive experimental validation using publicly available datasets MS-COCO and Wikiart. The results demonstrate that StyleStegan successfully mitigates the content leakage issue in serial and reversible style transfer tasks. The SSIM performance metrics for these tasks are 14.98% and 7.28% higher, respectively, compared to a suboptimal baseline model.