纹理增强通过高分辨率的风格转移为单图像超分辨率

I. Ahn, W. H. Nam
{"title":"纹理增强通过高分辨率的风格转移为单图像超分辨率","authors":"I. Ahn, W. H. Nam","doi":"10.2352/ISSN.2470-1173.2018.05.PMII-245","DOIUrl":null,"url":null,"abstract":"Recently, various deep-neural-network (DNN)-based approaches have been proposed for single-image super-resolution (SISR). Despite their promising results on major structure regions such as edges and lines, they still suffer from limited performance on texture regions that consist of very complex and fine patterns. This is because, during the acquisition of a low-resolution (LR) image via down-sampling, these regions lose most of the high frequency information necessary to represent the texture details. In this paper, we present a novel texture enhancement framework for SISR to effectively improve the spatial resolution in the texture regions as well as edges and lines. We call our method, high-resolution (HR) style transfer algorithm. Our framework consists of three steps: (i) generate an initial HR image from an interpolated LR image via an SISR algorithm, (ii) generate an HR style image from the initial HR image via down-scaling and tiling, and (iii) combine the HR style image with the initial HR image via a customized style transfer algorithm. Here, the HR style image is obtained by down-scaling the initial HR image and then repetitively tiling it into an image of the same size as the HR image. This down-scaling and tiling process comes from the idea that texture regions are often composed of small regions that similar in appearance albeit sometimes different in scale. This process creates an HR style image that is rich in details, which can be used to restore high-frequency texture details back into the initial HR image via the style transfer algorithm. Experimental results on a number of texture datasets show that our proposed HR style transfer algorithm provides more visually pleasing results compared with competitive methods.","PeriodicalId":309050,"journal":{"name":"Photography, Mobile, and Immersive Imaging","volume":"9 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":"{\"title\":\"Texture Enhancement via High-Resolution Style Transfer for Single-Image Super-Resolution\",\"authors\":\"I. Ahn, W. H. Nam\",\"doi\":\"10.2352/ISSN.2470-1173.2018.05.PMII-245\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Recently, various deep-neural-network (DNN)-based approaches have been proposed for single-image super-resolution (SISR). Despite their promising results on major structure regions such as edges and lines, they still suffer from limited performance on texture regions that consist of very complex and fine patterns. This is because, during the acquisition of a low-resolution (LR) image via down-sampling, these regions lose most of the high frequency information necessary to represent the texture details. In this paper, we present a novel texture enhancement framework for SISR to effectively improve the spatial resolution in the texture regions as well as edges and lines. We call our method, high-resolution (HR) style transfer algorithm. Our framework consists of three steps: (i) generate an initial HR image from an interpolated LR image via an SISR algorithm, (ii) generate an HR style image from the initial HR image via down-scaling and tiling, and (iii) combine the HR style image with the initial HR image via a customized style transfer algorithm. Here, the HR style image is obtained by down-scaling the initial HR image and then repetitively tiling it into an image of the same size as the HR image. This down-scaling and tiling process comes from the idea that texture regions are often composed of small regions that similar in appearance albeit sometimes different in scale. This process creates an HR style image that is rich in details, which can be used to restore high-frequency texture details back into the initial HR image via the style transfer algorithm. Experimental results on a number of texture datasets show that our proposed HR style transfer algorithm provides more visually pleasing results compared with competitive methods.\",\"PeriodicalId\":309050,\"journal\":{\"name\":\"Photography, Mobile, and Immersive Imaging\",\"volume\":\"9 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2016-12-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"4\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Photography, Mobile, and Immersive Imaging\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.2352/ISSN.2470-1173.2018.05.PMII-245\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Photography, Mobile, and Immersive Imaging","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.2352/ISSN.2470-1173.2018.05.PMII-245","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 4

摘要

近年来,人们提出了多种基于深度神经网络(DNN)的单图像超分辨率(SISR)方法。尽管它们在边缘和线条等主要结构区域上取得了令人鼓舞的结果,但在由非常复杂和精细的图案组成的纹理区域上,它们的性能仍然有限。这是因为,在通过下采样获取低分辨率(LR)图像期间,这些区域失去了表示纹理细节所需的大部分高频信息。本文提出了一种新的SISR纹理增强框架,可以有效地提高纹理区域以及边缘和线条的空间分辨率。我们称我们的方法为高分辨率(HR)风格迁移算法。我们的框架由三个步骤组成:(i)通过SISR算法从插值的LR图像生成初始HR图像,(ii)通过缩小和平装从初始HR图像生成HR风格图像,以及(iii)通过定制的风格转移算法将HR风格图像与初始HR图像结合起来。在这里,HR风格图像是通过缩小初始HR图像,然后将其重复平铺成与HR图像大小相同的图像来获得的。这种缩小和平铺的过程源于纹理区域通常由外观相似的小区域组成,尽管有时在规模上不同。这个过程创建了一个细节丰富的HR风格图像,该图像可以通过风格转移算法将高频纹理细节恢复到初始HR图像中。在多个纹理数据集上的实验结果表明,与竞争对手的方法相比,我们提出的HR风格迁移算法具有更好的视觉效果。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Texture Enhancement via High-Resolution Style Transfer for Single-Image Super-Resolution
Recently, various deep-neural-network (DNN)-based approaches have been proposed for single-image super-resolution (SISR). Despite their promising results on major structure regions such as edges and lines, they still suffer from limited performance on texture regions that consist of very complex and fine patterns. This is because, during the acquisition of a low-resolution (LR) image via down-sampling, these regions lose most of the high frequency information necessary to represent the texture details. In this paper, we present a novel texture enhancement framework for SISR to effectively improve the spatial resolution in the texture regions as well as edges and lines. We call our method, high-resolution (HR) style transfer algorithm. Our framework consists of three steps: (i) generate an initial HR image from an interpolated LR image via an SISR algorithm, (ii) generate an HR style image from the initial HR image via down-scaling and tiling, and (iii) combine the HR style image with the initial HR image via a customized style transfer algorithm. Here, the HR style image is obtained by down-scaling the initial HR image and then repetitively tiling it into an image of the same size as the HR image. This down-scaling and tiling process comes from the idea that texture regions are often composed of small regions that similar in appearance albeit sometimes different in scale. This process creates an HR style image that is rich in details, which can be used to restore high-frequency texture details back into the initial HR image via the style transfer algorithm. Experimental results on a number of texture datasets show that our proposed HR style transfer algorithm provides more visually pleasing results compared with competitive methods.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信