Neural Style Transfer for Vector Graphics

TL;DR

This paper introduces VectorNST, a novel neural style transfer method for vector graphics that employs new loss functions and differentiable rasterization, marking an early step in stylizing vector images.

Contribution

The paper proposes new loss functions and a differentiable rasterization-based method for neural style transfer in vector graphics, addressing limitations of standard approaches.

Findings

VectorNST effectively stylizes vector images compared to existing methods.

The approach demonstrates qualitative improvements over traditional bitmap style transfer.

The method provides a foundation for future research in vector image style transfer.

Abstract

Neural style transfer draws researchers' attention, but the interest focuses on bitmap images. Various models have been developed for bitmap image generation both online and offline with arbitrary and pre-trained styles. However, the style transfer between vector images has not almost been considered. Our research shows that applying standard content and style losses insignificantly changes the vector image drawing style because the structure of vector primitives differs a lot from pixels. To handle this problem, we introduce new loss functions. We also develop a new method based on differentiable rasterization that uses these loss functions and can change the color and shape parameters of the content image corresponding to the drawing of the style image. Qualitative experiments demonstrate the effectiveness of the proposed VectorNST method compared with the state-of-the-art neural style transfer approaches for bitmap images and the only existing approach for stylizing vector images, DiffVG. Although the proposed model does not achieve the quality and smoothness of style transfer between bitmap images, we consider our work an important early step in this area. VectorNST code and demo service are available at https://github.com/IzhanVarsky/VectorNST.