Neural Abstract Style Transfer for Chinese Traditional Painting

TL;DR

This paper introduces a neural style transfer method tailored for Chinese traditional paintings, effectively preserving their abstract qualities and style, and demonstrates superior results over existing methods.

Contribution

It proposes a novel MXDoG-guided filter and differentiable loss functions specifically designed for Chinese traditional painting style transfer.

Findings

Produces more appealing stylized results than state-of-the-art methods

Successfully preserves abstraction in style transfer

Provides a new dataset for Chinese traditional painting style transfer

Abstract

Chinese traditional painting is one of the most historical artworks in the world. It is very popular in Eastern and Southeast Asia due to being aesthetically appealing. Compared with western artistic painting, it is usually more visually abstract and textureless. Recently, neural network based style transfer methods have shown promising and appealing results which are mainly focused on western painting. It remains a challenging problem to preserve abstraction in neural style transfer. In this paper, we present a Neural Abstract Style Transfer method for Chinese traditional painting. It learns to preserve abstraction and other style jointly end-to-end via a novel MXDoG-guided filter (Modified version of the eXtended Difference-of-Gaussians) and three fully differentiable loss terms. To the best of our knowledge, there is little work study on neural style transfer of Chinese traditional painting. To promote research on this direction, we collect a new dataset with diverse photo-realistic images and Chinese traditional paintings. In experiments, the proposed method shows more appealing stylized results in transferring the style of Chinese traditional painting than state-of-the-art neural style transfer methods.