Constrained Neural Style Transfer for Decorated Logo Generation

TL;DR

This paper introduces a constrained neural style transfer method for generating decorated logos by preserving silhouettes and focusing style transfer around designated areas, improving logo uniqueness and quality.

Contribution

The paper presents a novel loss function based on distance transform to constrain style transfer, enhancing logo design by maintaining object silhouettes.

Findings

Effective preservation of silhouettes in logo generation

Enhanced control over style transfer localization

Generation of diverse, high-quality decorated logos

Abstract

Making decorated logos requires image editing skills, without sufficient skills, it could be a time-consuming task. While there are many on-line web services to make new logos, they have limited designs and duplicates can be made. We propose using neural style transfer with clip art and text for the creation of new and genuine logos. We introduce a new loss function based on distance transform of the input image, which allows the preservation of the silhouettes of text and objects. The proposed method constrains style transfer only around the designated area. We demonstrate the characteristics of proposed method. Finally, we show the results of logo generation with various input images.