# Chinese Paper-Cutting Style Transfer via Vision Transformer

## TL;DR

This paper introduces a new method using Vision Transformers to transfer the style of Chinese paper-cutting art onto images, preserving its unique visual characteristics.

## Contribution

A novel Transformer-based approach for Chinese paper-cutting style transfer with frequency-domain and contrastive learning modules.

## Key findings

- The proposed method outperforms existing state-of-the-art approaches in style transfer quality and consistency.
- The frequency-domain mixture block effectively preserves critical details and enhances style conversion.
- A new Chinese paper-cutting dataset is introduced to support future research in this area.

## Abstract

Style transfer technology has seen substantial attention in image synthesis, notably in applications like oil painting, digital printing, and Chinese landscape painting. However, it is often difficult to generate migrated images that retain the essence of paper-cutting art and have strong visual appeal when trying to apply the unique style of Chinese paper-cutting art to style transfer. Therefore, this paper proposes a new method for Chinese paper-cutting style transformation based on the Transformer, aiming at realizing the efficient transformation of Chinese paper-cutting art styles. Specifically, the network consists of a frequency-domain mixture block and a multi-level feature contrastive learning module. The frequency-domain mixture block explores spatial and frequency-domain interaction information, integrates multiple attention windows along with frequency-domain features, preserves critical details, and enhances the effectiveness of style conversion. To further embody the symmetrical structures and hollowed hierarchical patterns intrinsic to Chinese paper-cutting, the multi-level feature contrastive learning module is designed based on a contrastive learning strategy. This module maximizes mutual information between multi-level transferred features and content features, improves the consistency of representations across different layers, and thus accentuates the unique symmetrical aesthetics and artistic expression of paper-cutting. Extensive experimental results demonstrate that the proposed method outperforms existing state-of-the-art approaches in both qualitative and quantitative evaluations. Additionally, we created a Chinese paper-cutting dataset that, although modest in size, represents an important initial step towards enriching existing resources. This dataset provides valuable training data and a reference benchmark for future research in this field.