JND-LIC:基于人类视觉感知的可察觉差异的学习图像压缩

IF 4.8 1区 计算机科学 Q2 ENGINEERING, ELECTRICAL & ELECTRONIC
Zhaoqing Pan;Guoyu Zhang;Bo Peng;Jianjun Lei;Haoran Xie;Fu Lee Wang;Nam Ling
{"title":"JND-LIC:基于人类视觉感知的可察觉差异的学习图像压缩","authors":"Zhaoqing Pan;Guoyu Zhang;Bo Peng;Jianjun Lei;Haoran Xie;Fu Lee Wang;Nam Ling","doi":"10.1109/TBC.2024.3464413","DOIUrl":null,"url":null,"abstract":"Existing human visual perception-oriented image compression methods well maintain the perceptual quality of compressed images, but they may introduce fake details into the compressed images, and cannot dynamically improve the perceptual rate-distortion performance at the pixel level. To address these issues, a just noticeable difference (JND)-based learned image compression (JND-LIC) method is proposed for human visual perception in this paper, in which a weight-shared model is used to extract image features and JND features, and the learned JND features are utilized as perceptual prior knowledge to assist the image coding process. In order to generate a highly compact image feature representation, a JND-based feature transform module is proposed to model the pixel-to-pixel masking correlation between the image features and the JND features. Furthermore, inspired by eye movement research that the human visual system perceives image degradation unevenly, a JND-guided quantization mechanism is proposed for the entropy coding, which adjusts the quantization step of each pixel to further eliminate perceptual redundancies. Extensive experimental results show that our proposed JND-LIC significantly improves the perceptual quality of compressed images with fewer coding bits compared to state-of-the-art learned image compression methods. Additionally, the proposed method can be flexibly integrated with various advanced learned image compression methods, and has robust generalization capabilities to improve the efficiency of perceptual coding.","PeriodicalId":13159,"journal":{"name":"IEEE Transactions on Broadcasting","volume":"71 1","pages":"217-228"},"PeriodicalIF":4.8000,"publicationDate":"2024-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"JND-LIC: Learned Image Compression via Just Noticeable Difference for Human Visual Perception\",\"authors\":\"Zhaoqing Pan;Guoyu Zhang;Bo Peng;Jianjun Lei;Haoran Xie;Fu Lee Wang;Nam Ling\",\"doi\":\"10.1109/TBC.2024.3464413\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Existing human visual perception-oriented image compression methods well maintain the perceptual quality of compressed images, but they may introduce fake details into the compressed images, and cannot dynamically improve the perceptual rate-distortion performance at the pixel level. To address these issues, a just noticeable difference (JND)-based learned image compression (JND-LIC) method is proposed for human visual perception in this paper, in which a weight-shared model is used to extract image features and JND features, and the learned JND features are utilized as perceptual prior knowledge to assist the image coding process. In order to generate a highly compact image feature representation, a JND-based feature transform module is proposed to model the pixel-to-pixel masking correlation between the image features and the JND features. Furthermore, inspired by eye movement research that the human visual system perceives image degradation unevenly, a JND-guided quantization mechanism is proposed for the entropy coding, which adjusts the quantization step of each pixel to further eliminate perceptual redundancies. Extensive experimental results show that our proposed JND-LIC significantly improves the perceptual quality of compressed images with fewer coding bits compared to state-of-the-art learned image compression methods. Additionally, the proposed method can be flexibly integrated with various advanced learned image compression methods, and has robust generalization capabilities to improve the efficiency of perceptual coding.\",\"PeriodicalId\":13159,\"journal\":{\"name\":\"IEEE Transactions on Broadcasting\",\"volume\":\"71 1\",\"pages\":\"217-228\"},\"PeriodicalIF\":4.8000,\"publicationDate\":\"2024-09-27\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE Transactions on Broadcasting\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://ieeexplore.ieee.org/document/10697103/\",\"RegionNum\":1,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ENGINEERING, ELECTRICAL & ELECTRONIC\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Broadcasting","FirstCategoryId":"94","ListUrlMain":"https://ieeexplore.ieee.org/document/10697103/","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 0

摘要

现有的以人类视觉感知为导向的图像压缩方法能很好地保持压缩图像的感知质量,但可能会在压缩图像中引入虚假的细节,无法在像素级上动态提高感知率失真性能。为了解决这些问题,本文提出了一种基于JND的人类视觉感知学习图像压缩(JND- lic)方法,该方法使用权重共享模型提取图像特征和JND特征,并将学习到的JND特征作为感知先验知识来辅助图像编码过程。为了生成高度紧凑的图像特征表示,提出了一种基于JND的特征变换模块,对图像特征与JND特征之间的像素间掩蔽相关性进行建模。进一步,受人眼视觉系统感知图像退化不均匀的眼动研究启发,提出了一种基于jnd的熵编码量化机制,通过调整每个像素的量化步长,进一步消除感知冗余。大量的实验结果表明,与最先进的学习图像压缩方法相比,我们提出的JND-LIC以更少的编码位显著提高了压缩图像的感知质量。此外,该方法可以与各种先进的学习图像压缩方法灵活集成,并具有鲁棒的泛化能力,提高了感知编码的效率。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
JND-LIC: Learned Image Compression via Just Noticeable Difference for Human Visual Perception
Existing human visual perception-oriented image compression methods well maintain the perceptual quality of compressed images, but they may introduce fake details into the compressed images, and cannot dynamically improve the perceptual rate-distortion performance at the pixel level. To address these issues, a just noticeable difference (JND)-based learned image compression (JND-LIC) method is proposed for human visual perception in this paper, in which a weight-shared model is used to extract image features and JND features, and the learned JND features are utilized as perceptual prior knowledge to assist the image coding process. In order to generate a highly compact image feature representation, a JND-based feature transform module is proposed to model the pixel-to-pixel masking correlation between the image features and the JND features. Furthermore, inspired by eye movement research that the human visual system perceives image degradation unevenly, a JND-guided quantization mechanism is proposed for the entropy coding, which adjusts the quantization step of each pixel to further eliminate perceptual redundancies. Extensive experimental results show that our proposed JND-LIC significantly improves the perceptual quality of compressed images with fewer coding bits compared to state-of-the-art learned image compression methods. Additionally, the proposed method can be flexibly integrated with various advanced learned image compression methods, and has robust generalization capabilities to improve the efficiency of perceptual coding.
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
IEEE Transactions on Broadcasting
IEEE Transactions on Broadcasting 工程技术-电信学
CiteScore
9.40
自引率
31.10%
发文量
79
审稿时长
6-12 weeks
期刊介绍: The Society’s Field of Interest is “Devices, equipment, techniques and systems related to broadcast technology, including the production, distribution, transmission, and propagation aspects.” In addition to this formal FOI statement, which is used to provide guidance to the Publications Committee in the selection of content, the AdCom has further resolved that “broadcast systems includes all aspects of transmission, propagation, and reception.”
×
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:604180095
Book学术官方微信