Multiscale style transfer based on a Laplacian pyramid for traditional Chinese painting

TL;DR

This paper introduces a multiscale style transfer method based on Laplacian pyramids that effectively captures the unique patterns of traditional Chinese paintings by learning features at different scales, resulting in high-quality stylized images.

Contribution

The proposed approach uniquely combines Laplacian pyramid decomposition with a two-stage network to transfer Chinese painting styles across multiple scales, addressing limitations of previous methods.

Findings

Produces high-quality stylized images with traditional Chinese painting patterns.

Outperforms state-of-the-art style transfer methods in qualitative comparisons.

Effectively captures multiscale features for more natural stylization.

Abstract

Style transfer is adopted to synthesize appealing stylized images that preserve the structure of a content image but carry the pattern of a style image. Many recently proposed style transfer methods use only western oil paintings as style images to achieve image stylization. As a result, unnatural messy artistic effects are produced in stylized images when using these methods to directly transfer the patterns of traditional Chinese paintings, which are composed of plain colors and abstract objects. Moreover, most of them work only at the original image scale and thus ignore multiscale image information during training. In this paper, we present a novel effective multiscale style transfer method based on Laplacian pyramid decomposition and reconstruction, which can transfer unique patterns of Chinese paintings by learning different image features at different scales. In the first stage, the holistic patterns are transferred at low resolution by adopting a Style Transfer Base Network. Then, the details of the content and style are gradually enhanced at higher resolutions by a Detail Enhancement Network with an edge information selection (EIS) module in the second stage. The effectiveness of our method is demonstrated through the generation of appealing high-quality stylization results and a comparison with some state-of-the-art style transfer methods. Datasets and codes are available at https://github.com/toby-katakuri/LP_StyleTransferNet.