RAST: Restorable Arbitrary Style Transfer

Author:

Ma Yingnan1ORCID,Zhao Chenqiu1ORCID,Huang Bingran1ORCID,Li Xudong1ORCID,Basu Anup1ORCID

Affiliation:

1. University of Alberta, Canada

Abstract

The objective of arbitrary style transfer is to apply a given artistic or photo-realistic style to a target image. Although current methods have shown some success in transferring style, arbitrary style transfer still has several issues, including content leakage. Embedding an artistic style can result in unintended changes to the image content. This article proposes an iterative framework called Restorable Arbitrary Style Transfer (RAST) to effectively ensure content preservation and mitigate potential alterations to the content information. RAST can transmit both content and style information through multi-restorations and balance the content-style tradeoff in stylized images using the image restoration accuracy. To ensure RAST’s effectiveness, we introduce two novel loss functions: multi-restoration loss and style difference loss. We also propose a new quantitative evaluation method to assess content preservation and style embedding performance. Experimental results show that RAST outperforms state-of-the-art methods in generating stylized images that preserve content and embed style accurately.

Publisher

Association for Computing Machinery (ACM)

Subject

Computer Networks and Communications,Hardware and Architecture

Reference64 articles.

1. ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows

2. Understanding and Creating Art with AI: Review and Outlook

3. Haibo Chen Lei Zhao Zhizhong Wang Huiming Zhang Zhiwen Zuo Ailin Li Wei Xing and Dongming Lu. 2021. Artistic style transfer with internal-external learning and contrastive learning. Advances in Neural Information Processing Systems 34 (2021) 26561–26573.

4. Tian Qi Chen and Mark Schmidt. 2016. Fast patch-based style transfer of arbitrary style. arXiv:1612.04337. Retrieved from https://arxiv.org/abs/1612.04337

5. StarGAN: Unified Generative Adversarial Networks for Multi-domain Image-to-Image Translation

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3