基于swn - convn - unet和数据综合的实用盲图像去噪

IF 6.4 4区 计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS
Zhang, Kai, Li, Yawei, Liang, Jingyun, Cao, Jiezhang, Zhang, Yulun, Tang, Hao, Timofte, Radu, Van Gool, Luc
{"title":"基于swn - convn - unet和数据综合的实用盲图像去噪","authors":"Zhang, Kai, Li, Yawei, Liang, Jingyun, Cao, Jiezhang, Zhang, Yulun, Tang, Hao, Timofte, Radu, Van Gool, Luc","doi":"10.1007/s11633-023-1466-0","DOIUrl":null,"url":null,"abstract":"While recent years have witnessed a dramatic upsurge of exploiting deep neural networks toward solving image denoising, existing methods mostly rely on simple noise assumptions, such as additive white Gaussian noise (AWGN), JPEG compression noise and camera sensor noise, and a general-purpose blind denoising method for real images remains unsolved. In this paper, we attempt to solve this problem from the perspective of network architecture design and training data synthesis. Specifically, for the network architecture design, we propose a swin-conv block to incorporate the local modeling ability of residual convolutional layer and non-local modeling ability of swin transformer block, and then plug it as the main building block into the widely-used image-to-image translation UNet architecture. For the training data synthesis, we design a practical noise degradation model which takes into consideration different kinds of noise (including Gaussian, Poisson, speckle, JPEG compression, and processed camera sensor noises) and resizing, and also involves a random shuffle strategy and a double degradation strategy. Extensive experiments on AGWN removal and real image denoising demonstrate that the new network architecture design achieves state-of-the-art performance and the new degradation model can help to significantly improve the practicability. We believe our work can provide useful insights into current denoising research.","PeriodicalId":29727,"journal":{"name":"Machine Intelligence Research","volume":null,"pages":null},"PeriodicalIF":6.4000,"publicationDate":"2023-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"29","resultStr":"{\"title\":\"Practical Blind Image Denoising via Swin-Conv-UNet and Data Synthesis\",\"authors\":\"Zhang, Kai, Li, Yawei, Liang, Jingyun, Cao, Jiezhang, Zhang, Yulun, Tang, Hao, Timofte, Radu, Van Gool, Luc\",\"doi\":\"10.1007/s11633-023-1466-0\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"While recent years have witnessed a dramatic upsurge of exploiting deep neural networks toward solving image denoising, existing methods mostly rely on simple noise assumptions, such as additive white Gaussian noise (AWGN), JPEG compression noise and camera sensor noise, and a general-purpose blind denoising method for real images remains unsolved. In this paper, we attempt to solve this problem from the perspective of network architecture design and training data synthesis. Specifically, for the network architecture design, we propose a swin-conv block to incorporate the local modeling ability of residual convolutional layer and non-local modeling ability of swin transformer block, and then plug it as the main building block into the widely-used image-to-image translation UNet architecture. For the training data synthesis, we design a practical noise degradation model which takes into consideration different kinds of noise (including Gaussian, Poisson, speckle, JPEG compression, and processed camera sensor noises) and resizing, and also involves a random shuffle strategy and a double degradation strategy. Extensive experiments on AGWN removal and real image denoising demonstrate that the new network architecture design achieves state-of-the-art performance and the new degradation model can help to significantly improve the practicability. We believe our work can provide useful insights into current denoising research.\",\"PeriodicalId\":29727,\"journal\":{\"name\":\"Machine Intelligence Research\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":6.4000,\"publicationDate\":\"2023-09-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"29\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Machine Intelligence Research\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1007/s11633-023-1466-0\",\"RegionNum\":4,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"AUTOMATION & CONTROL SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Machine Intelligence Research","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1007/s11633-023-1466-0","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"AUTOMATION & CONTROL SYSTEMS","Score":null,"Total":0}
引用次数: 29

摘要

近年来,利用深度神经网络解决图像去噪问题的研究蓬勃发展,但现有的方法大多依赖于简单的噪声假设,如加性高斯白噪声(AWGN)、JPEG压缩噪声和相机传感器噪声,尚未解决实际图像的通用盲去噪方法。本文试图从网络架构设计和训练数据综合的角度来解决这一问题。具体来说,在网络架构设计上,我们提出了一种结合残差卷积层局部建模能力和swin变压器块非局部建模能力的swan -conv块,并将其作为主要构建块插入到广泛使用的图像到图像转换UNet体系结构中。对于训练数据的合成,我们设计了一个实用的噪声退化模型,该模型考虑了不同类型的噪声(包括高斯噪声、泊松噪声、散斑噪声、JPEG压缩噪声和处理后的相机传感器噪声)和大小调整,并涉及随机洗牌策略和双重退化策略。大量的AGWN去除和真实图像去噪实验表明,新的网络架构设计达到了最先进的性能,新的退化模型可以显著提高实用性。我们相信我们的工作可以为当前的去噪研究提供有用的见解。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Practical Blind Image Denoising via Swin-Conv-UNet and Data Synthesis
While recent years have witnessed a dramatic upsurge of exploiting deep neural networks toward solving image denoising, existing methods mostly rely on simple noise assumptions, such as additive white Gaussian noise (AWGN), JPEG compression noise and camera sensor noise, and a general-purpose blind denoising method for real images remains unsolved. In this paper, we attempt to solve this problem from the perspective of network architecture design and training data synthesis. Specifically, for the network architecture design, we propose a swin-conv block to incorporate the local modeling ability of residual convolutional layer and non-local modeling ability of swin transformer block, and then plug it as the main building block into the widely-used image-to-image translation UNet architecture. For the training data synthesis, we design a practical noise degradation model which takes into consideration different kinds of noise (including Gaussian, Poisson, speckle, JPEG compression, and processed camera sensor noises) and resizing, and also involves a random shuffle strategy and a double degradation strategy. Extensive experiments on AGWN removal and real image denoising demonstrate that the new network architecture design achieves state-of-the-art performance and the new degradation model can help to significantly improve the practicability. We believe our work can provide useful insights into current denoising research.
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
CiteScore
6.70
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