对条件流自适应的再思考一种新的图像超分辨率分布自适应策略

Maoyuan Xu, Tao Jia, Hongyang Zhou, Xiaobin Zhu
{"title":"对条件流自适应的再思考一种新的图像超分辨率分布自适应策略","authors":"Maoyuan Xu, Tao Jia, Hongyang Zhou, Xiaobin Zhu","doi":"10.1109/CoST57098.2022.00079","DOIUrl":null,"url":null,"abstract":"The conditional normalized flow model can alleviate the ill-posed nature of super-resolution problems by learning the conditional distribution of the output for a given low-resolution input, which allows multiple predictions for a given low-resolution image. However, the model may generate confusing artifacts in the high-frequency region of the image. While giving a smaller reduction in temperature would solve this problem, it would also smooth out the model's output, which would lead to a decrease in perceptual quality. In this paper, we propose a novel conditional normalizing flow-based distribution adaptation strategy for image Super-Resolution. More specifically, we demonstrate that the part of the latent variable that differs significantly between the latent variables of HR and the Bicubic of LR, contains mainly high-frequency information of the image. We adopt a Bicubic image of LR and a continuous threshold function to evaluate different temperatures in different latent variables. In this way, We can further alleviate generation of confusing artifacts without reducing perceptual quality. Extensive experiments show that our model can outperform state-of-the-art methods and generate more visually favorable results.","PeriodicalId":135595,"journal":{"name":"2022 International Conference on Culture-Oriented Science and Technology (CoST)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Rethinking the Adaptiveness of Conditional Flow A Novel Distribution Adaptation Strategy for Image Super-Resolution\",\"authors\":\"Maoyuan Xu, Tao Jia, Hongyang Zhou, Xiaobin Zhu\",\"doi\":\"10.1109/CoST57098.2022.00079\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The conditional normalized flow model can alleviate the ill-posed nature of super-resolution problems by learning the conditional distribution of the output for a given low-resolution input, which allows multiple predictions for a given low-resolution image. However, the model may generate confusing artifacts in the high-frequency region of the image. While giving a smaller reduction in temperature would solve this problem, it would also smooth out the model's output, which would lead to a decrease in perceptual quality. In this paper, we propose a novel conditional normalizing flow-based distribution adaptation strategy for image Super-Resolution. More specifically, we demonstrate that the part of the latent variable that differs significantly between the latent variables of HR and the Bicubic of LR, contains mainly high-frequency information of the image. We adopt a Bicubic image of LR and a continuous threshold function to evaluate different temperatures in different latent variables. In this way, We can further alleviate generation of confusing artifacts without reducing perceptual quality. Extensive experiments show that our model can outperform state-of-the-art methods and generate more visually favorable results.\",\"PeriodicalId\":135595,\"journal\":{\"name\":\"2022 International Conference on Culture-Oriented Science and Technology (CoST)\",\"volume\":\"25 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-08-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2022 International Conference on Culture-Oriented Science and Technology (CoST)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/CoST57098.2022.00079\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 International Conference on Culture-Oriented Science and Technology (CoST)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CoST57098.2022.00079","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

条件归一化流模型可以通过学习给定低分辨率输入的输出的条件分布来缓解超分辨率问题的病态性质,这允许对给定低分辨率图像进行多次预测。然而,该模型可能会在图像的高频区域产生令人困惑的伪影。虽然给出较小的温度降低可以解决这个问题,但它也会使模型的输出变得平滑,从而导致感知质量下降。本文提出了一种新的基于条件归一化流的图像超分辨率分布自适应策略。更具体地说,我们证明了HR潜变量与LR的双立方潜变量之间存在显著差异的部分主要包含图像的高频信息。我们采用LR的双三次图像和连续阈值函数来评估不同潜在变量下的不同温度。通过这种方式,我们可以在不降低感知质量的情况下进一步减少混淆伪像的产生。大量的实验表明,我们的模型可以优于最先进的方法,并产生更有利的视觉效果。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Rethinking the Adaptiveness of Conditional Flow A Novel Distribution Adaptation Strategy for Image Super-Resolution
The conditional normalized flow model can alleviate the ill-posed nature of super-resolution problems by learning the conditional distribution of the output for a given low-resolution input, which allows multiple predictions for a given low-resolution image. However, the model may generate confusing artifacts in the high-frequency region of the image. While giving a smaller reduction in temperature would solve this problem, it would also smooth out the model's output, which would lead to a decrease in perceptual quality. In this paper, we propose a novel conditional normalizing flow-based distribution adaptation strategy for image Super-Resolution. More specifically, we demonstrate that the part of the latent variable that differs significantly between the latent variables of HR and the Bicubic of LR, contains mainly high-frequency information of the image. We adopt a Bicubic image of LR and a continuous threshold function to evaluate different temperatures in different latent variables. In this way, We can further alleviate generation of confusing artifacts without reducing perceptual quality. Extensive experiments show that our model can outperform state-of-the-art methods and generate more visually favorable results.
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