SRAGAN: Saliency Regularized and Attended Generative Adversarial Network for Chinese Ink-wash Painting Style Transfer

TL;DR

This paper introduces SRAGAN, a novel GAN-based method for Chinese ink-wash painting style transfer that uses saliency detection to preserve content details and improve stylization quality.

Contribution

It integrates saliency detection into the I2I framework with new loss functions and normalization techniques to better preserve content and enhance style transfer in Chinese ink-wash paintings.

Findings

Outperforms existing methods in qualitative and quantitative evaluations.

Effectively preserves source image content during stylization.

Produces more vivid and delicate ink-wash textures.

Abstract

Recent style transfer problems are still largely dominated by Generative Adversarial Network (GAN) from the perspective of cross-domain image-to-image (I2I) translation, where the pivotal issue is to learn and transfer target-domain style patterns onto source-domain content images. This paper handles the problem of translating real pictures into traditional Chinese ink-wash paintings, i.e., Chinese ink-wash painting style transfer. Though a wide range of I2I models tackle this problem, a notable challenge is that the content details of the source image could be easily erased or corrupted due to the transfer of ink-wash style elements. To remedy this issue, we propose to incorporate saliency detection into the unpaired I2I framework to regularize image content, where the detected saliency map is utilized from two aspects: (\romannumeral1) we propose saliency IOU (SIOU) loss to explicitly regularize object content structure by enforcing saliency consistency before and after image stylization; (\romannumeral2) we propose saliency adaptive normalization (SANorm) which implicitly enhances object structure integrity of the generated paintings by dynamically injecting image saliency information into the generator to guide stylization process. Besides, we also propose saliency attended discriminator which harnesses image saliency information to focus generative adversarial attention onto the drawn objects, contributing to generating more vivid and delicate brush strokes and ink-wash textures. Extensive qualitative and quantitative experiments demonstrate superiority of our approach over related advanced image stylization methods in both GAN and diffusion model paradigms.