StyleStegan: Leak-free Style Transfer Based on Feature Steganography

TL;DR

StyleStegan introduces a leak-free style transfer method that embeds content features via steganography, enabling serial and reversible stylization while preventing content leakage.

Contribution

It presents a neural flow-based style transfer approach combined with steganography to prevent content leakage and enable reversible stylization.

Findings

Achieves 14.98% higher SSIM in serial stylization

Achieves 7.28% higher SSIM in reversible stylization

Effectively mitigates content leakage in style transfer

Abstract

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.