A Comprehensive Comparison between Neural Style Transfer and Universal Style Transfer

TL;DR

This paper compares neural style transfer and universal style transfer methods, evaluating their effectiveness in producing visually appealing images and their suitability for real-time applications.

Contribution

It provides a comprehensive comparison of two style transfer approaches, analyzing their performance, quality, and resource efficiency.

Findings

Neural style transfer with improvements offers high visual quality.

Universal style transfer provides better generalization to unseen styles.

Trade-offs exist between quality and computational efficiency.

Abstract

Style transfer aims to transfer arbitrary visual styles to content images. We explore algorithms adapted from two papers that try to solve the problem of style transfer while generalizing on unseen styles or compromised visual quality. Majority of the improvements made focus on optimizing the algorithm for real-time style transfer while adapting to new styles with considerably less resources and constraints. We compare these strategies and compare how they measure up to produce visually appealing images. We explore two approaches to style transfer: neural style transfer with improvements and universal style transfer. We also make a comparison between the different images produced and how they can be qualitatively measured.