Guided neural style transfer for shape stylization.

Gantugs Atarsaikhan,Brian Kenji Iwana,Seiichi Uchida,Alexandros Iosifidis

doi:10.1371/journal.pone.0233489

Abstract

Designing logos, typefaces, and other decorated shapes can require professional skills. In this paper, we aim to produce new and unique decorated shapes by stylizing ordinary shapes with machine learning. Specifically, we combined parametric and non-parametric neural style transfer algorithms to transfer both local and global features. Furthermore, we introduced a distance-based guiding to the neural style transfer process, so that only the foreground shape will be decorated. Lastly, qualitative evaluation and ablation studies are provided to demonstrate the usefulness of the proposed method.

Highlights

IntroductionDesigning decorated shapes (e.g. logos and typefaces) can require professional skills and can be time-consuming
Designing decorated shapes can require professional skills and can be time-consuming
Using a patch matching loss, we were able to transfer the local features that lack in the regular Neural Style Transfer (NST)

Summary

Introduction

Designing decorated shapes (e.g. logos and typefaces) can require professional skills and can be time-consuming. There exist applications, such as online tools [1, 2], that can be used for aided design. These tools generate logos by letting users choose from heuristic choices. Azadi et al [3] and Yang et al [4, 5] tried to generate stylized fonts and texts. These methods require prior training of the model for specific styles and fonts

Objectives

Results

Conclusion