TSSAT: Two-Stage Statistics-Aware Transformation for Artistic Style Transfer

TL;DR

This paper introduces TSSAT, a two-stage transformation method for artistic style transfer that mimics the drawing process, improving local style detail capture and global style consistency in stylized images.

Contribution

The paper proposes a novel two-stage statistics-aware transformation that aligns global and local style features, along with new loss functions for better content and style preservation.

Findings

Enhanced stylization effects demonstrated through experiments

Improved content preservation via attention-based content loss

Increased local style similarity with patch-based style loss

Abstract

Artistic style transfer aims to create new artistic images by rendering a given photograph with the target artistic style. Existing methods learn styles simply based on global statistics or local patches, lacking careful consideration of the drawing process in practice. Consequently, the stylization results either fail to capture abundant and diversified local style patterns, or contain undesired semantic information of the style image and deviate from the global style distribution. To address this issue, we imitate the drawing process of humans and propose a Two-Stage Statistics-Aware Transformation (TSSAT) module, which first builds the global style foundation by aligning the global statistics of content and style features and then further enriches local style details by swapping the local statistics (instead of local features) in a patch-wise manner, significantly improving the stylization effects. Moreover, to further enhance both content and style representations, we introduce two novel losses: an attention-based content loss and a patch-based style loss, where the former enables better content preservation by enforcing the semantic relation in the content image to be retained during stylization, and the latter focuses on increasing the local style similarity between the style and stylized images. Extensive qualitative and quantitative experiments verify the effectiveness of our method.