Article(id=1319955228246520274, tenantId=1146029695717560320, journalId=1278651732997652489, issueId=1319955013183586630, articleNumber=null, orderNo=null, doi=10.12086/oee.2026.250320, pmid=null, cstr=32245.14.oee.2026.250320, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1761580800000, receivedDateStr=2025-10-28, revisedDate=1769961600000, revisedDateStr=2026-02-02, acceptedDate=1770739200000, acceptedDateStr=2026-02-11, onlineDate=1792631449996, onlineDateStr=2026-10-22, pubDate=1779724800000, pubDateStr=2026-05-26, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1792631449996, onlineIssueDateStr=2026-10-22, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1792631449996, creator=13701087609, updateTime=1792631449996, updator=13701087609, issue=Issue{id=1319955013183586630, tenantId=1146029695717560320, journalId=1278651732997652489, year='2026', volume='53', issue='5', pageStart='250216', pageEnd='1', issueExtLink='null', onlineDate='null', pubDate='1779724800000', pubDateStr='2026-05-26', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1792631398721, creator='13701087609', updateTime=1792631398721, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext=null, issueFiles=null, downloadFileDto=null}, startPage=250320, endPage=1, ext={EN=ArticleExt(id=1319955228477206995, articleId=1319955228246520274, tenantId=1146029695717560320, journalId=1278651732997652489, language=EN, title=Target bitrate and image content-aware wide field-of-view light field image coding, columnId=1279511634116841602, journalTitle=Opto-Electronic Engineering, columnName=Article, runingTitle=null, highlight=null, articleAbstract=
Objective A sparse sampling mode set including key views and non-key views is constructed via the core strategy of sparse coding and reconstruction, providing fundamental support for the coding of wide-FOV light field images with variable bitrates. The specific implementation scheme is as follows: Firstly, the multi-dimensional complexity features of light field images are extracted, and an adaptive selection scheme for sparse sampling modes is designed combined with target bitrate constraints. Leveraging the K-nearest neighbor (KNN) algorithm, rapid matching of the optimal mode is enabled, allowing identification of the best sparse sampling strategy without traversing the entire mode set. On this basis, predictive relationships among key views are established, providing a more robust basis for subsequent coding and compression processes. Secondly, to address uneven view quality caused by traditional bitrate allocation methods, a frame-level bitrate pre-allocation strategy is designed according to the inter-frame spatial distance between the current encoded frame and its reference frames within the key view set. Dynamic adjustment of bitrate allocation weights effectively improves the angular quality consistency of the encoded views. Then, based on the I-frames in the key view set, the saliency detection and depth estimation techniques are integrated to generate largest coding unit (LCU)-level saliency weights. Utilizing the angular correlation of light field images, these weights are propagated to all key views along the angular dimension. Furthermore, saliency weights are combined with image regional complexity to develop a fine-grained LCU-level content-aware bitrate allocation strategy, achieving more accurate bitrate allocation. Finally, at the client side, key views are decoded according to the transmitted optimal sparse sampling mode, and non-key views are reconstructed using the decoded key views with a deep learning-based view synthesis network, ultimately completing the reconstruction of the wide-FOV light field image.
Methods In this paper, the core strategy of sparse coding and reconstruction is adopted to construct a sparse sampling mode set that includes key views and non-key views, thereby providing fundamental support for the coding of wide-FOV light field images with variable bitrates. The specific implementation scheme is as follows: Firstly, the multi-dimensional complexity features of light field images are extracted and an adaptive selection scheme is designed for sparse sampling modes in combination with target bitrate constraints. Leveraging the K-nearest neighbor (KNN) algorithm, this scheme enables the rapid matching of the optimal mode, which allows the identification of the best sparse sampling strategy without traversing the entire mode set. On this basis, the predictive relationships among key views are established, providing a more robust basis for subsequent coding and compression processes. Secondly, aiming to address the issue of uneven view quality caused by traditional bitrate allocation methods, a frame-level bitrate pre-allocation strategy is designed according to the inter-frame spatial distance between the current encoded frame and its reference frames within the key view set. By dynamically adjusting the bitrate allocation weights, this strategy effectively improves the angular quality consistency of the encoded views. Then, based on the I-frames in the key view set, the saliency detection and depth estimation techniques are integrated to generate LCU (largest coding unit)-level saliency weights. Utilizing the angular correlation of light field images, these weights are propagated to all key views along the angular dimension. Furthermore, the saliency weights are combined with the regional complexity of images to develop a fine-grained LCU-level content-aware bitrate allocation strategy, achieving more accurate bitrate allocation. Finally, at the client side, the key views are decoded according to the transmitted optimal sparse sampling mode, and the non-key views are reconstructed using the decoded key views with a deep learning-based view synthesis network, thus ultimately completing the reconstruction of the wide-FOV light field image.
Results and Discussions The proposed adaptive sparse sampling mode selection scheme, leveraging multi-dimensional feature fusion and deep learning prediction mechanisms, significantly reduces the computational complexity of mode selection and avoids exorbitant computational costs incurred by the traditional brute force search method. It rapidly matches diverse target bitrates and image content features to select the optimal or sub-optimal sparse coding mode. The designed two-level bitrate allocation strategy, combining frame-level pre-allocation and LCU-level perceptual allocation, effectively mitigates uneven angular view quality while maintaining compatibility with existing video coding standards, further enhancing the angular quality consistency of wide-FOV light field images. Experimental results show that, compared with existing representative methods, the method achieves an average bitrate saving of 45.284% and a peak signal-to-noise ratio (PSNR) improvement of 1.641 dB, with the maximum random access penalty of light field images limited to only 20.29%. These results indicate that the method not only improves coding efficiency but also ensures favorable random access performance, satisfying the demand for rapid view retrieval in practical applications.
Conclusions The proposed wide-FOV light field image coding method based on target bitrate and image content awareness effectively adapts to the coding requirements of variable bitrates and uncertain image content. It achieves satisfactory results in reducing sampling mode selection complexity and improving network transmission adaptability. Meanwhile, it fulfills multiple objectives including bitrate saving, image quality enhancement, angular quality consistency improvement, and random access capability optimization, demonstrating superior overall coding performance and favorable practical application value.
, authors=Lei Zhu, Yeyao Chen, Zheyu Feng, Panqi Jin, Gangyi Jiang, authorsList=Lei Zhu, Yeyao Chen, Zheyu Feng, Panqi Jin, Gangyi Jiang, authorCompany=null, correspAuthors=Gangyi Jiang, authorNote=null, correspAuthorsNote=
, copyrightStatement=Copyright © 2026 Opto-Electronic Engineering. All rights reserved., copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, fund=null), CN=ArticleExt(id=1319955245938094662, articleId=1319955228246520274, tenantId=1146029695717560320, journalId=1278651732997652489, language=CN, title=目标码率与图像内容感知的宽视场光场图像编码, columnId=1279511637858160772, journalTitle=光电工程, columnName=科研论文, runingTitle=null, highlight=null, articleAbstract=
宽视场光场成像能以更大视野反映场景中光线方向与强度信息,其巨大的数据量也对编码压缩技术提出更高要求。针对宽视场光场图像数据量大、目标码率可变及内容不确定的编码挑战,提出一种目标码率与图像内容感知的编码方法。首先,构建稀疏采样模式集,基于光场图像复杂度特征与目标码率约束,通过K近邻算法自适应优选最佳稀疏采样模式,降低选择复杂度;其次,以关键视图帧间距离为依据设计帧级码率分配策略,提升角度维质量一致性;最后,结合场景显著性、深度与区域复杂度,提出LCU级内容感知码率分配策略,实现细粒度资源优化。用户端通过深度学习网络重建非关键视图,获得完整光场图像。实验结果表明,所提方法能根据目标码率与光场图像内容快速地获得优选的稀疏采样模式,显著降低稀疏采样模式选择的复杂度,提升在网络传输条件变化下的宽视场光场图像编码性能;对比现有方法,平均实现45.284%码率节省与1.641 dB峰值信噪比提升,且角度维一致性得到增强,随机访问惩罚最高仅20.29%,表现出良好的综合编码性能。
, authors=朱磊, 陈晔曜, 封哲宇, 金攀麒, 蒋刚毅
*, *, authorsList=朱磊, 陈晔曜, 封哲宇, 金攀麒, 蒋刚毅, authorCompany=null, correspAuthors=蒋刚毅, authorNote=
作者贡献
朱磊:方法提出、论文撰写与修改、实验设计和数据整理;陈晔曜:论文审核与修改;封哲宇:实验数据校对与结果分析;金攀麒:实验数据收集与分析;蒋刚毅:论文选题指导、论文审核与修改。
, correspAuthorsNote=
, copyrightStatement=版权所有©《光电工程》编辑部 2026, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=US20An1JkjqnoIlNuyKtAg==, magXml=X00Dk8VvfYJH+5UGKdXicw==, pdfUrl=null, pdf=qLSPAmzie0lN8+jDMq2Klw==, pdfFileSize=14506317, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=p9Fl1cD72tSlYh1WwN/pjQ==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=MawTziRWYNUBBgdo84QPDQ==, mapNumber=null, fund=null)}, authors=[Author(id=1319955246323970635, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=zhulei2025@126.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1319955246403662413, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, authorId=1319955246323970635, language=EN, stringName=Lei Zhu, firstName=Lei, middleName=null, lastName=Zhu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Faculty of Information Science and Engineering, Ningbo, Zhejiang 315211, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1319955246479159886, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, authorId=1319955246323970635, language=CN, stringName=朱磊, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=宁波大学信息科学与工程学院,浙江 宁波 315211, bio={"img":"jDyWaE6v0c7kPngzeSrccQ==","content":"
朱磊 (2000-),男,硕士研究生,主要从事光场图像压缩等方面的研究。E-mail:zhulei2025@126.comzhulei2025@126.com
"}, bioImg=jDyWaE6v0c7kPngzeSrccQ==, bioContent=
朱磊 (2000-),男,硕士研究生,主要从事光场图像压缩等方面的研究。E-mail:zhulei2025@126.comzhulei2025@126.com
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1319955246227501639, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, xref=null, ext=[AuthorCompanyExt(id=1319955246235890248, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, companyId=1319955246227501639, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Faculty of Information Science and Engineering, Ningbo, Zhejiang 315211, China), AuthorCompanyExt(id=1319955246248473161, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, companyId=1319955246227501639, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=宁波大学信息科学与工程学院,浙江 宁波 315211)])]), Author(id=1319955246550463056, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=chenyeyao@nbu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1319955246621766226, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, authorId=1319955246550463056, language=EN, stringName=Yeyao Chen, firstName=Yeyao, middleName=null, lastName=Chen, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Faculty of Information Science and Engineering, Ningbo, Zhejiang 315211, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1319955246718235219, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, authorId=1319955246550463056, language=CN, stringName=陈晔曜, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=宁波大学信息科学与工程学院,浙江 宁波 315211, bio={"img":"U0vzAlFFPEDh2sYb5RwRTA==","content":"
陈晔曜 (1994-),男,博士,讲师,2023年于宁波大学获得博士学位,主要从事高动态范围图像/视频处理、光场图像处理及深度学习等方面的研究工作。E-mail:chenyeyao@nbu.edu.cnchenyeyao@nbu.edu.cn
"}, bioImg=U0vzAlFFPEDh2sYb5RwRTA==, bioContent=
陈晔曜 (1994-),男,博士,讲师,2023年于宁波大学获得博士学位,主要从事高动态范围图像/视频处理、光场图像处理及深度学习等方面的研究工作。E-mail:chenyeyao@nbu.edu.cnchenyeyao@nbu.edu.cn
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1319955246227501639, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, xref=null, ext=[AuthorCompanyExt(id=1319955246235890248, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, companyId=1319955246227501639, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Faculty of Information Science and Engineering, Ningbo, Zhejiang 315211, China), AuthorCompanyExt(id=1319955246248473161, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, companyId=1319955246227501639, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=宁波大学信息科学与工程学院,浙江 宁波 315211)])]), Author(id=1319955246848258645, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=15068368500@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1319955246965699159, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, authorId=1319955246848258645, language=EN, stringName=Zheyu Feng, firstName=Zheyu, middleName=null, lastName=Feng, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Faculty of Information Science and Engineering, Ningbo, Zhejiang 315211, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1319955247074751064, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, authorId=1319955246848258645, language=CN, stringName=封哲宇, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=宁波大学信息科学与工程学院,浙江 宁波 315211, bio={"img":"z1VEr15a6jB2ITcCnXZbgA==","content":"
封哲宇 (2000-),男,硕士研究生,主要从事光场图像压缩等方面的研究。E-mail:15068368500@163.com15068368500@163.com
"}, bioImg=z1VEr15a6jB2ITcCnXZbgA==, bioContent=
封哲宇 (2000-),男,硕士研究生,主要从事光场图像压缩等方面的研究。E-mail:15068368500@163.com15068368500@163.com
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1319955246227501639, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, xref=null, ext=[AuthorCompanyExt(id=1319955246235890248, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, companyId=1319955246227501639, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Faculty of Information Science and Engineering, Ningbo, Zhejiang 315211, China), AuthorCompanyExt(id=1319955246248473161, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, companyId=1319955246227501639, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=宁波大学信息科学与工程学院,浙江 宁波 315211)])]), Author(id=1319955247200580186, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1319955247292854876, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, authorId=1319955247200580186, language=EN, stringName=Panqi Jin, firstName=Panqi, middleName=null, lastName=Jin, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Faculty of Information Science and Engineering, Ningbo, Zhejiang 315211, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1319955247389323869, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, authorId=1319955247200580186, language=CN, stringName=金攀麒, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=宁波大学信息科学与工程学院,浙江 宁波 315211, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1319955246227501639, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, xref=null, ext=[AuthorCompanyExt(id=1319955246235890248, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, companyId=1319955246227501639, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Faculty of Information Science and Engineering, Ningbo, Zhejiang 315211, China), AuthorCompanyExt(id=1319955246248473161, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, companyId=1319955246227501639, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=宁波大学信息科学与工程学院,浙江 宁波 315211)])]), Author(id=1319955247481598559, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=jianggangyi@nbu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1319955247565484641, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, authorId=1319955247481598559, language=EN, stringName=Gangyi Jiang, firstName=Gangyi, middleName=null, lastName=Jiang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Faculty of Information Science and Engineering, Ningbo, Zhejiang 315211, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1319955247636787810, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, authorId=1319955247481598559, language=CN, stringName=蒋刚毅, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=
*, *, address=宁波大学信息科学与工程学院,浙江 宁波 315211, bio={"img":"XLbG59MouWFYsxlPSKpJxA==","content":"
蒋刚毅 (1964-),男,博士,教授,博士生导师,2000年于韩国Ajou大学获得博士学位,主要从事多媒体信号处理与通信、计算成像、视觉感知与编码、图像与视频质量评价等方面的研究工作。E-mail:jianggangyi@nbu.edu.cnjianggangyi@nbu.edu.cn
"}, bioImg=XLbG59MouWFYsxlPSKpJxA==, bioContent=
蒋刚毅 (1964-),男,博士,教授,博士生导师,2000年于韩国Ajou大学获得博士学位,主要从事多媒体信号处理与通信、计算成像、视觉感知与编码、图像与视频质量评价等方面的研究工作。E-mail:jianggangyi@nbu.edu.cnjianggangyi@nbu.edu.cn
, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1319955246227501639, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, xref=null, ext=[AuthorCompanyExt(id=1319955246235890248, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, companyId=1319955246227501639, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Faculty of Information Science and Engineering, Ningbo, Zhejiang 315211, China), AuthorCompanyExt(id=1319955246248473161, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, companyId=1319955246227501639, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=宁波大学信息科学与工程学院,浙江 宁波 315211)])])], keywords=[Keyword(id=1319955249507447396, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=EN, orderNo=1, keyword=wide field-of-view (FOV) light field images), Keyword(id=1319955249838797413, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=EN, orderNo=2, keyword=sparse sampling mode), Keyword(id=1319955249943655014, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=EN, orderNo=3, keyword=bitrate allocation strategy), Keyword(id=1319955250254033511, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=EN, orderNo=4, keyword=angular quality consistency), Keyword(id=1319955250329530985, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=CN, orderNo=1, keyword=宽视场光场图像), Keyword(id=1319955250694435433, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=CN, orderNo=2, keyword=稀疏采样模式), Keyword(id=1319955250786710122, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=CN, orderNo=3, keyword=码率分配策略), Keyword(id=1319955251101282924, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=CN, orderNo=4, keyword=角度维质量一致性)], refs=[Reference(id=1319955267559731874, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=1, rfOrder=0, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Y Y, Jiang G Y, Jin C C, et al. Multi-Attention learning and exposure guidance toward ghost-free high dynamic range light field imaging[J].
IEEE Trans Visual Comput Graph, 2025,
31 (9): 5304−5320., articleTitle=null, refAbstract=null), Reference(id=1319955267928830627, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=2, rfOrder=1, authorNames=null, journalName=null, refType=null, unstructuredReference=罗少聪, 张旭东, 万乐, 等. 结合图像特征迁移的光场深度估计方法[J]. 计算机工程, 2023,
49 (4): 206−216., articleTitle=null, refAbstract=null), Reference(id=1319955268331483812, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=2, rfOrder=2, authorNames=null, journalName=null, refType=null, unstructuredReference=Luo S C, Zhang X D, Wan L, et al. Light field depth estimation method combining image feature transfer[J].
Comput Eng, 2023,
49 (4): 206−216., articleTitle=null, refAbstract=null), Reference(id=1319955268465701541, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=3, rfOrder=3, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhou W H, Lin L L, Hong Y J, et al. Beyond photometric consistency: geometry-based occlusion-aware unsupervised light field disparity estimation[J].
IEEE Trans Neural Netw Learn Syst, 2024,
35 (11): 15660−15674., articleTitle=null, refAbstract=null), Reference(id=1319955271225553574, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=4, authorNames=null, journalName=null, refType=null, unstructuredReference=黄莉, 吕天琪, 武迎春, 等. 基于双路引导更新的光场图像超分网络[J]. 光电工程, 2024,
51 (12): 240222., articleTitle=null, refAbstract=null), Reference(id=1319955271624012455, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=5, authorNames=null, journalName=null, refType=null, unstructuredReference=Huang L, Lv T Q, Wu Y C, et al. Two-way guided updating network for light field image super-resolution[J].
Opto-Electron Eng, 2024,
51 (12): 240222., articleTitle=null, refAbstract=null), Reference(id=1319955271699509928, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=6, authorNames=null, journalName=null, refType=null, unstructuredReference=吕天琪, 武迎春, 赵贤凌. 角度差异强化的光场图像超分网络[J]. 光电工程, 2023,
50 (2): 220185., articleTitle=null, refAbstract=null), Reference(id=1319955271770813097, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=7, authorNames=null, journalName=null, refType=null, unstructuredReference=Lv T Q, Wu Y C, Zhao X L. Light field image super-resolution network based on angular difference enhancement[J].
Opto-Electron Eng, 2023,
50 (2): 220185., articleTitle=null, refAbstract=null), Reference(id=1319955272118940330, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=8, authorNames=null, journalName=null, refType=null, unstructuredReference=Samarakoon T, Abeywardena K, Edussooriya C U S. Arbitrary volumetric refocusing of dense and sparse light fields[Z]. arXiv: 2502.19238, 2025. https://doi.org/10.48550/arXiv.2502.19238., articleTitle=null, refAbstract=null), Reference(id=1319955272186049195, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=9, authorNames=null, journalName=null, refType=null, unstructuredReference=Zheng X, Li Z Q, Liu D Y, et al. Spatial attention-guided light field salient object detection network with implicit neural representation[J].
IEEE Trans Circuits Syst Video Technol, 2024,
34 (12): 12437−12449., articleTitle=null, refAbstract=null), Reference(id=1319955272483844780, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=10, authorNames=null, journalName=null, refType=null, unstructuredReference=钟长祥, 陈晔曜, 朱仲杰, 等. 基于深度感知的无监督大视场光场内容生成[J]. 激光与光电子学进展, 2025,
62 (12): 1211001., articleTitle=null, refAbstract=null), Reference(id=1319955272584508077, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=11, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhong C X, Chen Y Y, Zhu Z J, et al. Unsupervised large field of view light field content generation based on depth perception[J].
Laser Optoelectron Prog, 2025,
62 (12): 1211001., articleTitle=null, refAbstract=null), Reference(id=1319955272945218222, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=12, authorNames=null, journalName=null, refType=null, unstructuredReference=Cui Y L, Jiang G Y, Yu M, et al. Stitched wide field of view light field image quality assessment: benchmark database and objective metric[J].
IEEE Trans Multimed, 2024,
26: 5092−5107., articleTitle=null, refAbstract=null), Reference(id=1319955273045881519, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=13, authorNames=null, journalName=null, refType=null, unstructuredReference=Mukati M U, Zhang X, Wu X L, et al. Low-complexity ℓ∞-compression of light field images with a deep-decompression stage[J].
J Vis Commun Image Represent, 2024,
99: 104072., articleTitle=null, refAbstract=null), Reference(id=1319955273326899888, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=14, authorNames=null, journalName=null, refType=null, unstructuredReference=Perra C, Assuncao P. High efficiency coding of light field images based on tiling and pseudo-temporal data arrangement[C]//
2016 IEEE International Conference on Multimedia & Expo Workshops (ICMEW), Seattle, 2016: 1–4. https://doi.org/10.1109/ICMEW.2016.7574671., articleTitle=null, refAbstract=null), Reference(id=1319955273398203057, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=15, authorNames=null, journalName=null, refType=null, unstructuredReference=Dai F, Zhang J, Ma Y K, et al. Lenselet image compression scheme based on subaperture images streaming[C]//
2015 IEEE International Conference on Image Processing, Quebec City, 2015: 4733–4737. https://doi.org/10.1109/ICIP.2015.7351705., articleTitle=null, refAbstract=null), Reference(id=1319955273469506226, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=16, authorNames=null, journalName=null, refType=null, unstructuredReference=Conceição R, Porto M, Zatt B, et al. LF-CAE: Context-adaptive encoding for lenslet light fields using HEVC[C]//
2018 25th IEEE International Conference on Image Processing (ICIP), Athens, 2018: 3174–3178. https://doi.org/10.1109/ICIP.2018.8451345., articleTitle=null, refAbstract=null), Reference(id=1319955273792467635, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=17, authorNames=null, journalName=null, refType=null, unstructuredReference=Li L, Li Z, Li, B, et al. Pseudo-sequence-based 2-D Hierarchical coding structure for light-field image compression[J].
IEEE J Sel Top Signal Process, 2017,
11 (7): 1107−1119., articleTitle=null, refAbstract=null), Reference(id=1319955273888936628, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=18, authorNames=null, journalName=null, refType=null, unstructuredReference=Yu Z Y, Qu Q, Zheng W, et al. Efficient light field transmission via enhanced resampling reconstruction and angular attention estimation[J].
ACM Trans Sensor Netw, 2025., articleTitle=null, refAbstract=null), Reference(id=1319955273960239797, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=19, authorNames=null, journalName=null, refType=null, unstructuredReference=Huang X P, An P, Chen Y L, et al. Low bitrate light field compression with geometry and content consistency[J].
IEEE Trans Multimed, 2022,
24: 152−165., articleTitle=null, refAbstract=null), Reference(id=1319955274018960054, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=20, authorNames=null, journalName=null, refType=null, unstructuredReference=Bakir N, Hamidouche W, Fezza S A, et al. Light field image coding using VVC standard and view synthesis based on dual discriminator GAN[J].
IEEE Trans Multimed, 2021,
23: 2972−2985., articleTitle=null, refAbstract=null), Reference(id=1319955274211898039, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=21, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu D Y, Huang Y, Fang Y M, et al. Multi-stream dense view reconstruction network for light field image compression[J].
IEEE Trans Multimed, 2023,
25: 4400−4414., articleTitle=null, refAbstract=null), Reference(id=1319955274287395512, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=22, authorNames=null, journalName=null, refType=null, unstructuredReference=金攀琪. 基于稀疏模式选择的光场图像编码方法: 中国, 2024112825009[P]. 2025-01-14, articleTitle=null, refAbstract=null), Reference(id=1319955274367087289, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=Tong K D, Jin X, Wang C, et al. SADN: Learned light field image compression with spatial-angular decorrelation[C]//
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Singapore, 2022: 1870–1874. https://doi.org/10.1109/ICASSP43922.2022.9747377., articleTitle=null, refAbstract=null), Reference(id=1319955274580996794, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=24, authorNames=null, journalName=null, refType=null, unstructuredReference=Feng S Y, Zhang Y, Zhu L W, et al. LFIC-DRASC: Deep light field image compression using disentangled representation and asymmetrical strip convolution[J].
IEEE Trans Broadcast, 2025,
71 (3): 889−902., articleTitle=null, refAbstract=null), Reference(id=1319955274681660091, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=25, authorNames=null, journalName=null, refType=null, unstructuredReference=Takhtardeshir S, Olsson R, Guillemot C, et al. Efficient and fast light field compression via VAE-based spatial and angular disentanglement[J].
IEEE Access, 2025,
13: 18594−18607., articleTitle=null, refAbstract=null), Reference(id=1319955274769740476, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang G Z, Zhu Y H, Wang H N, et al. Extracting motion and appearance via inter-frame attention for efficient video frame interpolation[C]//
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, 2023: 5682–5692. https://doi.org/10.1109/CVPR52729.2023.00550., articleTitle=null, refAbstract=null), Reference(id=1319955275033981629, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=27, authorNames=null, journalName=null, refType=null, unstructuredReference=M. Řeřábek and T. Ebrahimi, New Light Field Image Dataset[C]//8th International Conference on Quality of Multimedia Experience (QoMEX), Lisbon, Portugal, 2016. https://www.epfl.ch/labs/mmspg/downloads/epfl-light-field-image-dataset/, articleTitle=null, refAbstract=null), Reference(id=1319955275117867710, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=28, authorNames=null, journalName=null, refType=null, unstructuredReference=Honauer K, Johannsen O, Kondermann D, et al. A dataset and evaluation methodology for depth estimation on 4D light fields[C]//
Proceedings of 13th Asian Conference on Computer Vision Computer Vision – ACCV 2016, Taipei, 2017: 19–34. https://doi.org/10.1007/978-3-319-54187-7_2., articleTitle=null, refAbstract=null), Reference(id=1319955275428246207, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=29, authorNames=null, journalName=null, refType=null, unstructuredReference=Li J, Wang Z M, Lai S M, et al. Parallax-tolerant image stitching based on robust elastic warping[J].
IEEE Trans Multimed, 2018,
20 (7): 1672−1687., articleTitle=null, refAbstract=null), Reference(id=1319955275507937984, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=27, rfOrder=30, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhou R, Jiang G Y, Chen Y, et al. Benchmark database and objective metric for wide-field-of-view light field image quality measurement[J].
IEEE Trans Instrum Meas, 2026,
75: 1−15, articleTitle=null, refAbstract=null), Reference(id=1319955275914785473, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=28, rfOrder=31, authorNames=null, journalName=null, refType=null, unstructuredReference=Miangoleh S M H, Dille S, Mai L, et al. Boosting monocular depth estimation models to high-resolution via content-adaptive multi-resolution merging[C]//
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, 2021: 9680–9689. https://doi.org/10.1109/CVPR46437.2021.00956., articleTitle=null, refAbstract=null), Reference(id=1319955276300661442, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=29, rfOrder=32, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang F Y, Pan J S, Xu S K, et al. Learning discriminative cross-modality features for RGB-D saliency detection[J].
IEEE Trans Image Process, 2022,
31: 1285−1297., articleTitle=null, refAbstract=null), Reference(id=1319955276392936131, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=30, rfOrder=33, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Z, Dong M J, Guan X H, et al. Fast ISP coding mode optimization algorithm based on CU texture complexity for VVC[J].
EURASIP J Image Video Process, 2021,
2021 (1): 24., articleTitle=null, refAbstract=null), Reference(id=1319955276464239300, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=31, rfOrder=34, authorNames=null, journalName=null, refType=null, unstructuredReference=Amirpour H, Guillemot C, Ghanbari M, et al. Advanced scalability for light field image coding[J].
IEEE Trans Image Process, 2022,
31: 7435−7448., articleTitle=null, refAbstract=null), Reference(id=1319955276539736773, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=32, rfOrder=35, authorNames=null, journalName=null, refType=null, unstructuredReference=Majid M, Owais M, Anwar S M. Visual saliency based redundancy allocation in HEVC compatible multiple description video coding[J].
Multimed Tools Appl, 2018,
77 (16): 20955−20977., articleTitle=null, refAbstract=null), Reference(id=1319955276615234246, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=33, rfOrder=36, authorNames=null, journalName=null, refType=null, unstructuredReference=Bjontegaard G. Calculation of average PSNR differences between RD-curves[S]. ITU SG16 Doc. VCEG-M33, 2001., articleTitle=null, refAbstract=null), Reference(id=1319955276694926023, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=34, rfOrder=37, authorNames=null, journalName=null, refType=null, unstructuredReference=Pereira F, Pagliari C, da Silva E A B, et al. JPEG Pleno light field coding common test conditions v3.3: ISO/IEC 21794–1[S]. 2021., articleTitle=null, refAbstract=null), Reference(id=1319955276791395016, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=35, rfOrder=38, authorNames=null, journalName=null, refType=null, unstructuredReference=Wanner S, Meister S, Goldluecke B. Datasets and benchmarks for densely sampled 4D light fields[C]//
Proceedings of Vision, Modeling, and Visualization (VMV), 2013: 225–226. https://doi.org/10.2312/PE.VMV.VMV13.225-226., articleTitle=null, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1319955246227501639, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, xref=null, ext=[AuthorCompanyExt(id=1319955246235890248, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, companyId=1319955246227501639, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Faculty of Information Science and Engineering, Ningbo, Zhejiang 315211, China), AuthorCompanyExt(id=1319955246248473161, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, companyId=1319955246227501639, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=宁波大学信息科学与工程学院,浙江 宁波 315211)])], figs=[ArticleFig(id=1319955251587822191, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=EN, label=Fig.1, caption=
Framework of the proposed wide field-of-view (FOV) light field image coding method with target bitrate and content awareness, figureFileSmall=ZExir5PSKuMT1cVFRNPhMQ==, figureFileBig=p9Fl1cD72tSlYh1WwN/pjQ==, tableContent=null), ArticleFig(id=1319955251935949424, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=CN, label=图1, caption=
所提目标码率与图像内容感知的宽视场光场图像编码方法框图, figureFileSmall=ZExir5PSKuMT1cVFRNPhMQ==, figureFileBig=p9Fl1cD72tSlYh1WwN/pjQ==, tableContent=null), ArticleFig(id=1319955255756960377, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=EN, label=Fig.2, caption=
Set M of sparse sampling modes for the light field image, figureFileSmall=b20ZzqZn9TXYjFwIDjOnNQ==, figureFileBig=c0M0VAPInjw/J1jcICyKRg==, tableContent=null), ArticleFig(id=1319955255882789498, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=CN, label=图2, caption=
光场图像的稀疏采样模式集合M, figureFileSmall=b20ZzqZn9TXYjFwIDjOnNQ==, figureFileBig=c0M0VAPInjw/J1jcICyKRg==, tableContent=null), ArticleFig(id=1319955255975064187, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=EN, label=Fig.3, caption=
Center views of the light field images from the training and testing light field image sets. (a) Training light field image set; (b) Test light field image set, figureFileSmall=exUOtK/9Uutalg439B8pgg==, figureFileBig=gm+HrdXmg8x0Rk5EjDv3fg==, tableContent=null), ArticleFig(id=1319955256079921788, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=CN, label=图3, caption=
训练与测试光场图像集合的光场图像中心视图。 (a) 训练集中代表性光场图像集合; (b) 测试光场图像集合, figureFileSmall=exUOtK/9Uutalg439B8pgg==, figureFileBig=gm+HrdXmg8x0Rk5EjDv3fg==, tableContent=null), ArticleFig(id=1319955256151224957, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=EN, label=Fig.4, caption=
Saliency region difference maps. (a) Central view; (b) Saliency map of the central view; (c) Difference between the central-view saliency map and the top-left-view saliency map; (d) Difference between the central-view saliency map and the bottom-right-view saliency map; (e) Difference between the top-left-view saliency map and the bottom-right-view saliency map, figureFileSmall=37QQGSGEYv6VJwEjBDr3GA==, figureFileBig=miC4soUWhN9hf3V3ZtYTAA==, tableContent=null), ArticleFig(id=1319955256243499646, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=CN, label=图4, caption=
显著性区域差值图。 (a)中心视图; (b)中心视图的显著图; (c)中心视图显著图与左上角视图显著图的差值; (d)中心视图显著性图与右下角显著性值差值; (e)左上角显著性图与右下角显著性图差值, figureFileSmall=37QQGSGEYv6VJwEjBDr3GA==, figureFileBig=miC4soUWhN9hf3V3ZtYTAA==, tableContent=null), ArticleFig(id=1319955256335774335, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=EN, label=Fig.5, caption=
Progressive reconstruction process of L'non (using M1 as an example, where red blocks indicate the encoded key views L'key). (a) Initial reconstruction of {S'1,5、S'5,5、S'5,1、S'5,9、S'9,5}; (b) Second and third stages of progressive reconstruction, taking the top-left region as an example, figureFileSmall=rRNjKR7BntQgzI1Jk+kARw==, figureFileBig=Jr5CzM94FnKmCbu2lmv7gQ==, tableContent=null), ArticleFig(id=1319955256411271808, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=CN, label=图5, caption=
L'non的渐进式重建过程 (以M1为例,红色块为编码后的关键视图L'key)。 (a)初次重建{S'1,5、S'5,5、S'5,1、S'5,9、S'9,5}; (b)以左上角为例的第2、3次渐近重建, figureFileSmall=rRNjKR7BntQgzI1Jk+kARw==, figureFileBig=Jr5CzM94FnKmCbu2lmv7gQ==, tableContent=null), ArticleFig(id=1319955256495157889, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=EN, label=Fig.6, caption=
Comparison of rate-distortion performance of different coding methods under the PPSNR metric. (a) I01; (b) I02; (c) I03; (d) I04; (e) I05; (f) I06; (g) I07; (h) I08, figureFileSmall=umuyg3XfG5lKLTz28pHoNw==, figureFileBig=rnMlLpyJXgZLlTBy+WWyDA==, tableContent=null), ArticleFig(id=1319955256587432578, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=CN, label=图6, caption=
不同编码方法在PPSNR指标下的率失真性能对比。 (a) I01; (b) I02; (c) I03; (d) I04; (e) I05; (f) I06; (g) I07; (h) I08, figureFileSmall=umuyg3XfG5lKLTz28pHoNw==, figureFileBig=rnMlLpyJXgZLlTBy+WWyDA==, tableContent=null), ArticleFig(id=1319955257824752259, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=EN, label=Fig.7, caption=
Comparison of rate-distortion performance of different coding methods under the PSNR metric. (a) I01; (b) I02; (c) I03; (d) I04; (e) I05; (f) I06; (g) I07; (h) I08, figureFileSmall=DpmG02NvVUeBbktiAAPFEw==, figureFileBig=bh1JeXmuH/HzIVyO+6wHIw==, tableContent=null), ArticleFig(id=1319955257917026948, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=CN, label=图7, caption=
不同编码方法在PSNR指标下的率失真性能对比。 (a) I01; (b) I02; (c) I03; (d) I04; (e) I05; (f) I06; (g) I07; (h) I08, figureFileSmall=DpmG02NvVUeBbktiAAPFEw==, figureFileBig=bh1JeXmuH/HzIVyO+6wHIw==, tableContent=null), ArticleFig(id=1319955258214822533, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=EN, label=Fig.8, caption=
Subjective comparison of I-frame decoding for light field scene I02. The proposed method uses a bitrate of 0.00527 bpp, while CAE [13], LSM[12], and RSM[12] use a bitrate of 0.00506 bpp. (a) Visual comparison results of salient regions; (b) Visual comparison results of non-salient but content-complex regions, figureFileSmall=9u2WEy59nuipjnUFydiDZw==, figureFileBig=EAW/5P6b/E5rpW3Gpks8xg==, tableContent=null), ArticleFig(id=1319955258298708614, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=CN, label=图8, caption=
光场图像场景I02的I帧解码主观感知对比。所提方法的码率分别为0.00527 bpp,CAE[13]、LSM[12]以及RSM[12]方法码率为0.00506 bpp。 (a)显著性区域视觉对比结果; (b)非显著但内容复杂区域视觉对比结果, figureFileSmall=9u2WEy59nuipjnUFydiDZw==, figureFileBig=EAW/5P6b/E5rpW3Gpks8xg==, tableContent=null), ArticleFig(id=1319955258374206087, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=EN, label=Fig.9, caption=
Random access penalty at different bitrates, figureFileSmall=M7zjWoZLjfC7ck5pbBsdYA==, figureFileBig=+/7ZhwxvzJFHZmu7mSO/YA==, tableContent=null), ArticleFig(id=1319955258680390280, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=CN, label=图9, caption=
不同码率下随机访问惩罚, figureFileSmall=M7zjWoZLjfC7ck5pbBsdYA==, figureFileBig=+/7ZhwxvzJFHZmu7mSO/YA==, tableContent=null), ArticleFig(id=1319955259078849161, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=EN, label=Fig.10, caption=
Comparison of angular quality consistency. (a) I01, bitrate with quality consistency enabled; 0.00244 bpp, without quality consistency; 0.00270 bpp; (b) I01, bitrate with quality consistency enabled; 0.10042 bpp, without quality consistency: 0.10180 bpp, figureFileSmall=M38Rh42FNcenYc5IOBBl6g==, figureFileBig=x7d1fFWuHf+Al+UpNFbxgQ==, tableContent=null), ArticleFig(id=1319955259150152330, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=CN, label=图10, caption=
角度维质量一致对比。 (a) 光场图像I01,开启质量一致调节码率为0.00244 bpp,未开启码率为0.00270 bpp; (b) 光场图像I01,开启质量一致调节码率为0.10042 bpp,未开启码率为0.10180 bpp, figureFileSmall=M38Rh42FNcenYc5IOBBl6g==, figureFileBig=x7d1fFWuHf+Al+UpNFbxgQ==, tableContent=null), ArticleFig(id=1319955259477308043, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=EN, label=Tab.1, caption=
Optimal sparse sampling patterns at different bitrates (R1–R5 denote increasing levels)
, figureFileSmall=null, figureFileBig=null, tableContent=
| Scenes | R1 | R2 | R3 | R4 | R5 |
|---|
| I01 | M1 | M2 | M4 | M5 | M5 |
| I02 | M1 | M2 | M3 | M5 | M6 |
| I03 | M2 | M2 | M3 | M5 | M6 |
| I04 | M1 | M1 | M3 | M5 | M6 |
), ArticleFig(id=1319955259884155532, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=CN, label=表1, caption=
不同目标码率下的最佳稀疏采样模式 (R1至R5表示目标码率值逐渐增大)
, figureFileSmall=null, figureFileBig=null, tableContent=
| Scenes | R1 | R2 | R3 | R4 | R5 |
|---|
| I01 | M1 | M2 | M4 | M5 | M5 |
| I02 | M1 | M2 | M3 | M5 | M6 |
| I03 | M2 | M2 | M3 | M5 | M6 |
| I04 | M1 | M1 | M3 | M5 | M6 |
), ArticleFig(id=1319955259963847309, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=EN, label=Tab.2, caption=
Coding performance comparison of the proposed and other wide-FOV light field methods using PPSNR
, figureFileSmall=null, figureFileBig=null, tableContent=
| Scenes | Proposed vs RSM[12] | | Proposed vs LSM[12] | | Proposed vs CAE[13] | | Proposed vs Ref. [19] | | Proposed vs BFS |
|---|
| BD-BR/% | BD-PPSNR/dB | | BD-BR/% | BD-PPSNR/dB | | BD-BR/% | BD-PPSNR/dB | | BD-BR/% | BD-PPSNR/dB | | BD-BR/% | BD-PPSNR/dB |
|---|
| I01 | −56.257 | +2.537 | | −54.762 | +2.365 | | −46.198 | +1.988 | | −1.607 | +0.060 | | +0.814 | −0.025 |
| I02 | −61.663 | +2.673 | | −56.565 | +2.215 | | −59.262 | +2.407 | | −10.972 | +0.265 | | +0.000 | +0.000 |
| I03 | −78.745 | +2.806 | | −74.183 | +2.405 | | −72.536 | +2.330 | | −7.717 | +0.133 | | +0.000 | +0.000 |
| I04 | −63.761 | +3.006 | | −59.969 | +2.668 | | −57.751 | +2.511 | | +0.680 | −0.005 | | +0.828 | −0.026 |
| I05 | −62.943 | +2.868 | | −65.727 | +2.928 | | −58.891 | +2.515 | | −4.647 | +0.125 | | +0.000 | +0.000 |
| I06 | −75.373 | +3.140 | | −75.681 | +2.996 | | −73.104 | +2.824 | | −9.398 | +0.121 | | +0.443 | −0.012 |
| I07 | −68.072 | +3.094 | | −66.476 | +2.899 | | −63.831 | +2.780 | | −7.847 | +0.233 | | +0.660 | −0.016 |
| I08 | −65.631 | +3.264 | | −63.998 | +3.143 | | −60.181 | +2.863 | | −1.505 | +0.022 | | +2.351 | −0.066 |
| Avg. | −66.556 | +2.923 | | −64.670 | +2.702 | | −61.469 | +2.527 | | −5.377 | +0.119 | | +0.637 | −0.018 |
), ArticleFig(id=1319955260324557454, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=CN, label=表2, caption=
所提方法与其他宽视场光场图像编码方法在PPSNR指标上的编码性能对比
, figureFileSmall=null, figureFileBig=null, tableContent=
| Scenes | Proposed vs RSM[12] | | Proposed vs LSM[12] | | Proposed vs CAE[13] | | Proposed vs Ref. [19] | | Proposed vs BFS |
|---|
| BD-BR/% | BD-PPSNR/dB | | BD-BR/% | BD-PPSNR/dB | | BD-BR/% | BD-PPSNR/dB | | BD-BR/% | BD-PPSNR/dB | | BD-BR/% | BD-PPSNR/dB |
|---|
| I01 | −56.257 | +2.537 | | −54.762 | +2.365 | | −46.198 | +1.988 | | −1.607 | +0.060 | | +0.814 | −0.025 |
| I02 | −61.663 | +2.673 | | −56.565 | +2.215 | | −59.262 | +2.407 | | −10.972 | +0.265 | | +0.000 | +0.000 |
| I03 | −78.745 | +2.806 | | −74.183 | +2.405 | | −72.536 | +2.330 | | −7.717 | +0.133 | | +0.000 | +0.000 |
| I04 | −63.761 | +3.006 | | −59.969 | +2.668 | | −57.751 | +2.511 | | +0.680 | −0.005 | | +0.828 | −0.026 |
| I05 | −62.943 | +2.868 | | −65.727 | +2.928 | | −58.891 | +2.515 | | −4.647 | +0.125 | | +0.000 | +0.000 |
| I06 | −75.373 | +3.140 | | −75.681 | +2.996 | | −73.104 | +2.824 | | −9.398 | +0.121 | | +0.443 | −0.012 |
| I07 | −68.072 | +3.094 | | −66.476 | +2.899 | | −63.831 | +2.780 | | −7.847 | +0.233 | | +0.660 | −0.016 |
| I08 | −65.631 | +3.264 | | −63.998 | +3.143 | | −60.181 | +2.863 | | −1.505 | +0.022 | | +2.351 | −0.066 |
| Avg. | −66.556 | +2.923 | | −64.670 | +2.702 | | −61.469 | +2.527 | | −5.377 | +0.119 | | +0.637 | −0.018 |
), ArticleFig(id=1319955260429415055, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=EN, label=Tab.3, caption=
Coding performance comparison of the proposed and other wide-FOV light field methods using PSNR
, figureFileSmall=null, figureFileBig=null, tableContent=
| Scenes | Proposed vs RSM[12] | | Proposed vs LSM[12] | | Proposed vs CAE[13] | | Proposed vs Ref. [19] | | Proposed vs BFS |
|---|
| BD-BR/% | BD-PSNR/dB | | BD-BR/% | BD-PSNR/dB | | BD-BR/% | BD-PSNR/dB | | BD-BR/% | BD-PSNR/dB | | BD-BR/% | BD-PSNR/dB |
|---|
| I01 | −37.875 | +1.480 | | −36.481 | +1.435 | | −30.831 | +1.183 | | −4.454 | +0.194 | | +4.528 | −0.138 |
| I02 | −42.290 | +1.471 | | −35.726 | +1.175 | | −32.937 | +1.092 | | −7.345 | +0.196 | | +0.000 | −0.000 |
| I03 | −43.322 | +1.070 | | −45.205 | +1.235 | | −41.416 | +1.009 | | −1.192 | +0.029 | | +0.000 | −0.000 |
| I04 | −46.524 | +1.896 | | −38.929 | +1.523 | | −41.524 | +1.639 | | −0.423 | +0.034 | | +3.558 | −0.123 |
| I05 | −48.528 | +1.929 | | −42.787 | +1.636 | | −44.458 | +1.720 | | −9.014 | +0.262 | | +0.000 | −0.000 |
| I06 | −55.287 | +1.832 | | −54.942 | +1.841 | | −51.087 | +1.662 | | −11.887 | +0.280 | | +1.215 | −0.033 |
| I07 | −48.390 | +1.855 | | −46.590 | +1.774 | | −43.678 | +1.622 | | −5.297 | +0.179 | | +0.647 | −0.018 |
| I08 | −40.058 | +1.595 | | −38.041 | +1.489 | | −33.608 | +1.291 | | −2.849 | +0.074 | | +3.418 | −0.088 |
| Avg. | −45.284 | +1.641 | | −42.337 | +1.513 | | −39.942 | +1.402 | | −5.307 | +0.156 | | +1.671 | −0.050 |
), ArticleFig(id=1319955260819485328, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=CN, label=表3, caption=
所提方法与其他宽视场光场图像编码方法在PSNR指标上的编码性能对比
, figureFileSmall=null, figureFileBig=null, tableContent=
| Scenes | Proposed vs RSM[12] | | Proposed vs LSM[12] | | Proposed vs CAE[13] | | Proposed vs Ref. [19] | | Proposed vs BFS |
|---|
| BD-BR/% | BD-PSNR/dB | | BD-BR/% | BD-PSNR/dB | | BD-BR/% | BD-PSNR/dB | | BD-BR/% | BD-PSNR/dB | | BD-BR/% | BD-PSNR/dB |
|---|
| I01 | −37.875 | +1.480 | | −36.481 | +1.435 | | −30.831 | +1.183 | | −4.454 | +0.194 | | +4.528 | −0.138 |
| I02 | −42.290 | +1.471 | | −35.726 | +1.175 | | −32.937 | +1.092 | | −7.345 | +0.196 | | +0.000 | −0.000 |
| I03 | −43.322 | +1.070 | | −45.205 | +1.235 | | −41.416 | +1.009 | | −1.192 | +0.029 | | +0.000 | −0.000 |
| I04 | −46.524 | +1.896 | | −38.929 | +1.523 | | −41.524 | +1.639 | | −0.423 | +0.034 | | +3.558 | −0.123 |
| I05 | −48.528 | +1.929 | | −42.787 | +1.636 | | −44.458 | +1.720 | | −9.014 | +0.262 | | +0.000 | −0.000 |
| I06 | −55.287 | +1.832 | | −54.942 | +1.841 | | −51.087 | +1.662 | | −11.887 | +0.280 | | +1.215 | −0.033 |
| I07 | −48.390 | +1.855 | | −46.590 | +1.774 | | −43.678 | +1.622 | | −5.297 | +0.179 | | +0.647 | −0.018 |
| I08 | −40.058 | +1.595 | | −38.041 | +1.489 | | −33.608 | +1.291 | | −2.849 | +0.074 | | +3.418 | −0.088 |
| Avg. | −45.284 | +1.641 | | −42.337 | +1.513 | | −39.942 | +1.402 | | −5.307 | +0.156 | | +1.671 | −0.050 |
), ArticleFig(id=1319955261188584081, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=EN, label=Tab.4, caption=
Maximum bitrate required to access any view of each light field image at different bitrates
, figureFileSmall=null, figureFileBig=null, tableContent=
| Scenes | R1 | R2 | R3 | R4 | R5 |
|---|
| I01 | 0.0021 | 0.0027 | 0.0076 | 0.0327 | 0.1425 |
| I02 | 0.0022 | 0.0025 | 0.0085 | 0.0284 | 0.1526 |
| I03 | 0.0016 | 0.0022 | 0.0072 | 0.0236 | 0.1395 |
| I04 | 0.0021 | 0.0024 | 0.0081 | 0.0364 | 0.1483 |
| I05 | 0.0021 | 0.0036 | 0.0102 | 0.0311 | 0.1454 |
| I06 | 0.0020 | 0.0029 | 0.0077 | 0.0319 | 0.1512 |
| I07 | 0.0020 | 0.0026 | 0.0098 | 0.0377 | 0.1467 |
| I08 | 0.0021 | 0.0025 | 0.0082 | 0.0345 | 0.1155 |
| Avg. | 0.0020 | 0.0026 | 0.0084 | 0.0328 | 0.1427 |
), ArticleFig(id=1319955261268275858, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=CN, label=表4, caption=
不同码率下每个光场图像访问任一视图所需最多码率
, figureFileSmall=null, figureFileBig=null, tableContent=
| Scenes | R1 | R2 | R3 | R4 | R5 |
|---|
| I01 | 0.0021 | 0.0027 | 0.0076 | 0.0327 | 0.1425 |
| I02 | 0.0022 | 0.0025 | 0.0085 | 0.0284 | 0.1526 |
| I03 | 0.0016 | 0.0022 | 0.0072 | 0.0236 | 0.1395 |
| I04 | 0.0021 | 0.0024 | 0.0081 | 0.0364 | 0.1483 |
| I05 | 0.0021 | 0.0036 | 0.0102 | 0.0311 | 0.1454 |
| I06 | 0.0020 | 0.0029 | 0.0077 | 0.0319 | 0.1512 |
| I07 | 0.0020 | 0.0026 | 0.0098 | 0.0377 | 0.1467 |
| I08 | 0.0021 | 0.0025 | 0.0082 | 0.0345 | 0.1155 |
| Avg. | 0.0020 | 0.0026 | 0.0084 | 0.0328 | 0.1427 |
), ArticleFig(id=1319955261654151827, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=EN, label=Tab.5, caption=
The RAP values of the proposed method in different scenes
, figureFileSmall=null, figureFileBig=null, tableContent=
| Scenes | R1/% | R2/% | R2/% | R4/% | R5/% |
|---|
| I01 | 84.30 | 54.62 | 38.53 | 32.71 | 19.05 |
| I02 | 88.50 | 50.11 | 42.50 | 28.40 | 20.29 |
| I03 | 73.40 | 46.80 | 38.70 | 27.30 | 18.60 |
| I04 | 84.70 | 48.70 | 40.50 | 36.40 | 19.77 |
| I05 | 84.10 | 72.50 | 51.25 | 31.13 | 19.38 |
| I06 | 80.60 | 58.18 | 38.51 | 31.97 | 20.16 |
| I07 | 80.22 | 52.57 | 49.31 | 37.70 | 19.56 |
| I08 | 84.00 | 50.41 | 41.01 | 34.58 | 15.54 |
| Avg. | 80.11 | 52.50 | 42.22 | 32.81 | 19.03 |
), ArticleFig(id=1319955262010667668, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=CN, label=表5, caption=
所提方法在不同场景下的RAP值
, figureFileSmall=null, figureFileBig=null, tableContent=
| Scenes | R1/% | R2/% | R2/% | R4/% | R5/% |
|---|
| I01 | 84.30 | 54.62 | 38.53 | 32.71 | 19.05 |
| I02 | 88.50 | 50.11 | 42.50 | 28.40 | 20.29 |
| I03 | 73.40 | 46.80 | 38.70 | 27.30 | 18.60 |
| I04 | 84.70 | 48.70 | 40.50 | 36.40 | 19.77 |
| I05 | 84.10 | 72.50 | 51.25 | 31.13 | 19.38 |
| I06 | 80.60 | 58.18 | 38.51 | 31.97 | 20.16 |
| I07 | 80.22 | 52.57 | 49.31 | 37.70 | 19.56 |
| I08 | 84.00 | 50.41 | 41.01 | 34.58 | 15.54 |
| Avg. | 80.11 | 52.50 | 42.22 | 32.81 | 19.03 |
), ArticleFig(id=1319955262413320853, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=EN, label=Tab.6, caption=
Quality variance of the decoded light field images
, figureFileSmall=null, figureFileBig=null, tableContent=
| Scenes | R1 | | R2 | | R3 | | R4 |
|---|
| Nonuse | Use | | Nonuse | Use | | Nonuse | Use | | Nonuse | Use |
|---|
| I01 | 0.308 | 0.166 | | 0.315 | 0.188 | | 0.434 | 0.160 | | 0.434 | 0.160 |
| I02 | 0.412 | 0.212 | | 0.388 | 0.251 | | 0.631 | 0.151 | | 0.534 | 0.297 |
| I03 | 0.311 | 0.114 | | 0.214 | 0.127 | | 0.314 | 0.108 | | 0.802 | 0.244 |
| I04 | 0.295 | 0.182 | | 0.319 | 0.106 | | 0.721 | 0.201 | | 1.122 | 0.552 |
| I05 | 0.451 | 0.241 | | 0.596 | 0.101 | | 0.225 | 0.053 | | 0.709 | 0.257 |
| I06 | 0.332 | 0.123 | | 0.411 | 0.097 | | 0.224 | 0.065 | | 0.922 | 0.351 |
| I07 | 0.360 | 0.201 | | 0.099 | 0.058 | | 0.536 | 0.091 | | 0.812 | 0.211 |
| I08 | 0.191 | 0.099 | | 0.223 | 0.094 | | 0.342 | 0.108 | | 0.851 | 0.425 |
), ArticleFig(id=1319955262501401238, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=CN, label=表6, caption=
解码光场图像的质量方差值
, figureFileSmall=null, figureFileBig=null, tableContent=
| Scenes | R1 | | R2 | | R3 | | R4 |
|---|
| Nonuse | Use | | Nonuse | Use | | Nonuse | Use | | Nonuse | Use |
|---|
| I01 | 0.308 | 0.166 | | 0.315 | 0.188 | | 0.434 | 0.160 | | 0.434 | 0.160 |
| I02 | 0.412 | 0.212 | | 0.388 | 0.251 | | 0.631 | 0.151 | | 0.534 | 0.297 |
| I03 | 0.311 | 0.114 | | 0.214 | 0.127 | | 0.314 | 0.108 | | 0.802 | 0.244 |
| I04 | 0.295 | 0.182 | | 0.319 | 0.106 | | 0.721 | 0.201 | | 1.122 | 0.552 |
| I05 | 0.451 | 0.241 | | 0.596 | 0.101 | | 0.225 | 0.053 | | 0.709 | 0.257 |
| I06 | 0.332 | 0.123 | | 0.411 | 0.097 | | 0.224 | 0.065 | | 0.922 | 0.351 |
| I07 | 0.360 | 0.201 | | 0.099 | 0.058 | | 0.536 | 0.091 | | 0.812 | 0.211 |
| I08 | 0.191 | 0.099 | | 0.223 | 0.094 | | 0.342 | 0.108 | | 0.851 | 0.425 |
), ArticleFig(id=1319955262870499991, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=EN, label=Tab.7, caption=
Analysis of sparse sampling mode selection
, figureFileSmall=null, figureFileBig=null, tableContent=
| Scenes | R1 | | R2 | | R3 | | R4 | | R5 |
|---|
| Pro. | Jin | BFS | | Pro. | Jin | BFS | | Pro. | Jin | BFS | | Pro. | Jin | BFS | | Pro. | Jin | BFS |
|---|
| I01 | M1 | M2 | M1 | | M2 | M1 | M2 | | M3 | M3 | M4 | | M5 | M5 | M5 | | M5 | M5 | M5 |
| I02 | M1 | M1 | M1 | | M2 | M2 | M2 | | M3 | M2 | M3 | | M5 | M5 | M5 | | M6 | M6 | M6 |
| I03 | M2 | M1 | M2 | | M2 | M2 | M2 | | M3 | M4 | M3 | | M5 | M5 | M5 | | M6 | M6 | M6 |
| I04 | M1 | M1 | M1 | | M1 | M1 | M1 | | M3 | M2 | M3 | | M4 | M4 | M5 | | M6 | M6 | M6 |
| I05 | M1 | M1 | M1 | | M2 | M2 | M2 | | M3 | M2 | M3 | | M4 | M4 | M4 | | M6 | M6 | M6 |
| I06 | M1 | M1 | M2 | | M2 | M1 | M2 | | M3 | M2 | M3 | | M5 | M4 | M5 | | M5 | M6 | M5 |
| I07 | M1 | M2 | M1 | | M2 | M2 | M2 | | M4 | M2 | M4 | | M5 | M5 | M5 | | M5 | M6 | M6 |
| I08 | M1 | M1 | M1 | | M1 | M2 | M1 | | M3 | M3 | M4 | | M5 | M5 | M5 | | M6 | M6 | M6 |
), ArticleFig(id=1319955262954386072, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=CN, label=表7, caption=
稀疏采样模式选择分析
, figureFileSmall=null, figureFileBig=null, tableContent=
| Scenes | R1 | | R2 | | R3 | | R4 | | R5 |
|---|
| Pro. | Jin | BFS | | Pro. | Jin | BFS | | Pro. | Jin | BFS | | Pro. | Jin | BFS | | Pro. | Jin | BFS |
|---|
| I01 | M1 | M2 | M1 | | M2 | M1 | M2 | | M3 | M3 | M4 | | M5 | M5 | M5 | | M5 | M5 | M5 |
| I02 | M1 | M1 | M1 | | M2 | M2 | M2 | | M3 | M2 | M3 | | M5 | M5 | M5 | | M6 | M6 | M6 |
| I03 | M2 | M1 | M2 | | M2 | M2 | M2 | | M3 | M4 | M3 | | M5 | M5 | M5 | | M6 | M6 | M6 |
| I04 | M1 | M1 | M1 | | M1 | M1 | M1 | | M3 | M2 | M3 | | M4 | M4 | M5 | | M6 | M6 | M6 |
| I05 | M1 | M1 | M1 | | M2 | M2 | M2 | | M3 | M2 | M3 | | M4 | M4 | M4 | | M6 | M6 | M6 |
| I06 | M1 | M1 | M2 | | M2 | M1 | M2 | | M3 | M2 | M3 | | M5 | M4 | M5 | | M5 | M6 | M5 |
| I07 | M1 | M2 | M1 | | M2 | M2 | M2 | | M4 | M2 | M4 | | M5 | M5 | M5 | | M5 | M6 | M6 |
| I08 | M1 | M1 | M1 | | M1 | M2 | M1 | | M3 | M3 | M4 | | M5 | M5 | M5 | | M6 | M6 | M6 |
), ArticleFig(id=1319955263378010777, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=EN, label=Tab.8, caption=
Comparison of computational time between the proposed method and BFS method/s
, figureFileSmall=null, figureFileBig=null, tableContent=
| Method | R1 | R2 | R3 | R4 | R5 |
|---|
| BFS | 6834.9 | 7902.6 | 9998.2 | 15494.7 | 19645.4 |
| Algorithm 1 | 22.7 | 22.7 | 22.7 | 22.7 | 22.7 |
| Proposed | 425.6 | 526.1 | 996.8 | 2953.78 | 12511.9 |
), ArticleFig(id=1319955263675806362, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=CN, label=表8, caption=
所提方法与BFS方法在实际运行时间上的对比/s
, figureFileSmall=null, figureFileBig=null, tableContent=
| Method | R1 | R2 | R3 | R4 | R5 |
|---|
| BFS | 6834.9 | 7902.6 | 9998.2 | 15494.7 | 19645.4 |
| Algorithm 1 | 22.7 | 22.7 | 22.7 | 22.7 | 22.7 |
| Proposed | 425.6 | 526.1 | 996.8 | 2953.78 | 12511.9 |
), ArticleFig(id=1319955263763886747, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=EN, label=Tab.9, caption=
The test results of the proposed method on the HCI old dataset
, figureFileSmall=null, figureFileBig=null, tableContent=
| Method | Accuracy/% |
|---|
| HCI old | Jin | 66.7 |
| BFS | 100.0 |
| Proposed | 80.0 |
), ArticleFig(id=1319955263839384220, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=CN, label=表9, caption=
所提方法在HCI old数据集上测试的结果
, figureFileSmall=null, figureFileBig=null, tableContent=
| Method | Accuracy/% |
|---|
| HCI old | Jin | 66.7 |
| BFS | 100.0 |
| Proposed | 80.0 |
), ArticleFig(id=1319955264082653853, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=EN, label=Tab.10, caption=
Comparison of coding performance in terms of PSNR between the proposed method and other methods on the HCI old dataset
, figureFileSmall=null, figureFileBig=null, tableContent=
| Method | BD-BR/% | BD-PSNR/dB |
|---|
| Proposed vs | BFS | +1.604 | −0.070 |
| Jin | −4.638 | +0.131 |
), ArticleFig(id=1319955266611819166, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=CN, label=表10, caption=
所提方法在HCI old数据集上与其他方法在PSNR指标上的编码性能对比
, figureFileSmall=null, figureFileBig=null, tableContent=
| Method | BD-BR/% | BD-PSNR/dB |
|---|
| Proposed vs | BFS | +1.604 | −0.070 |
| Jin | −4.638 | +0.131 |
), ArticleFig(id=1319955267018666656, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=EN, label=Tab.11, caption=
Ablation experiments of different modules
, figureFileSmall=null, figureFileBig=null, tableContent=
| Method | KNN | FR | LCU | Evaluation |
|---|
| PSNR/dB↑ | PPSNR/dB↑ | Var↓ |
|---|
| Baseline | | | | 36.441 | 37.994 | 1.122 |
| No.1 | √ | | | 37.640 | 38.221 | 1.647 |
| No.2 | √ | √ | | 37.740 | 38.412 | 0.138 |
| No.3 | √ | √ | √ | 37.825 | 39.297 | 0.151 |
), ArticleFig(id=1319955267127718561, tenantId=1146029695717560320, journalId=1278651732997652489, articleId=1319955228246520274, language=CN, label=表11, caption=
不同模块的消融实验
, figureFileSmall=null, figureFileBig=null, tableContent=
| Method | KNN | FR | LCU | Evaluation |
|---|
| PSNR/dB↑ | PPSNR/dB↑ | Var↓ |
|---|
| Baseline | | | | 36.441 | 37.994 | 1.122 |
| No.1 | √ | | | 37.640 | 38.221 | 1.647 |
| No.2 | √ | √ | | 37.740 | 38.412 | 0.138 |
| No.3 | √ | √ | √ | 37.825 | 39.297 | 0.151 |
)], attaches=null, journal=Journal(id=1278641367198941188, delFlag=0, nameCn=光电工程, nameEn=Opto-Electronic Engineering, nameHistory1=null, nameHistory2=null, issn=1003-501X, eissn=2097-4019, cn=51-1346/O4, coden=null, periodic=0, language=CN, oaType=null, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=4Vimkd+qXLWNxtdpr9mFNw==, journalPrice=null, startedYear=null, abbrevIsoEn=Opto-Electronic Engineering, journalRemark=null, publicationField=null, createdTime=1782781457950, updatedTime=1784021784694, createdBy=18614031015, updatedBy=13041195026, firstLetterCn=G, firstLetterEn=G, subjectCode=Engineering, subjectName=null, subjectCodeEn=Engineering, subjectNameEn=null, picCn=4Vimkd+qXLWNxtdpr9mFNw==, picEn=vAq9s20WLs1ODDfbWq+Gjg==, jcr=null, cjcr=null, exts=[JournalExt(id=1283843675721536154, language=CN, name=光电工程, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1784021784954, updatedTime=1784021784954, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.manuscripts.com.cn/gdgc, submissionEditorUrl=http://www.manuscripts.com.cn/gdgc, submissionReviewUrl=http://www.manuscripts.com.cn/gdgc, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1283843675771867803, language=EN, name=Opto-Electronic Engineering, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1784021784966, updatedTime=1784021784966, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.manuscripts.com.cn/gdgc, submissionEditorUrl=http://www.manuscripts.com.cn/gdgc, submissionReviewUrl=http://www.manuscripts.com.cn/gdgc, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1278651732997652489, websiteList=[Website(id=1278723867418018151, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1278651732997652489, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/oee/CN, language=CN, createTime=1782801127533, createBy=18614031015, updateTime=1782804494442, updateBy=18614031015, name=光电工程-中文, tplId=1146099689490845704, title=光电工程, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1278738091150128034, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1278723867418018151, code=articleTextType, value=kx, createTime=1782804518735, updateTime=1782804518735, creator=18614031015, updator=18614031015), WebsiteProps(id=1278738091120767903, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1278723867418018151, code=banner, value=null, createTime=1782804518728, updateTime=1782804518728, creator=18614031015, updator=18614031015), WebsiteProps(id=1278738091171099557, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1278723867418018151, code=grayFlag, value=0, createTime=1782804518740, updateTime=1782804518740, creator=18614031015, updator=18614031015), WebsiteProps(id=1278738091108184990, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1278723867418018151, code=logo, value=https://castjournals.cast.org.cn/joweb/oee/CN/file/pic?fileId=A1C6uwqtMazluiWkEpR0Mg==, createTime=1782804518725, updateTime=1782804518725, creator=18614031015, updator=18614031015), WebsiteProps(id=1278738091179488167, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1278723867418018151, code=minRunFlag, value=0, createTime=1782804518742, updateTime=1782804518742, creator=18614031015, updator=18614031015), WebsiteProps(id=1278738091141739425, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1278723867418018151, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/oee/CN/file/pic, createTime=1782804518733, updateTime=1782804518733, creator=18614031015, updator=18614031015), WebsiteProps(id=1278738091175293862, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1278723867418018151, code=silenceFlag, value=0, createTime=1782804518741, updateTime=1782804518741, creator=18614031015, updator=18614031015), WebsiteProps(id=1278738091129156512, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1278723867418018151, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1782804518730, updateTime=1782804518730, creator=18614031015, updator=18614031015), WebsiteProps(id=1278738091154322339, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1278723867418018151, code=themeColor, value=null, createTime=1782804518736, updateTime=1782804518736, creator=18614031015, updator=18614031015), WebsiteProps(id=1278738091162710948, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1278723867418018151, code=themeStyle, value=null, createTime=1782804518738, updateTime=1782804518738, creator=18614031015, updator=18614031015)]), Website(id=1278723867522875769, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1278651732997652489, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/oee/EN, language=EN, createTime=1782801127558, createBy=18614031015, updateTime=1782804490442, updateBy=18614031015, name=光电工程-英文, tplId=1146101810881728533, title=Opto-Electronic Engineering, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1278738063660659607, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1278723867522875769, code=articleTextType, value=kx, createTime=1782804512181, updateTime=1782804512181, creator=18614031015, updator=18614031015), WebsiteProps(id=1278738063635493780, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1278723867522875769, code=banner, value=null, createTime=1782804512175, updateTime=1782804512175, creator=18614031015, updator=18614031015), WebsiteProps(id=1278738063924900762, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1278723867522875769, code=grayFlag, value=0, createTime=1782804512244, updateTime=1782804512244, creator=18614031015, updator=18614031015), WebsiteProps(id=1278738063606133651, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1278723867522875769, code=logo, value=https://castjournals.cast.org.cn/joweb/oee/EN/file/pic?fileId=A1C6uwqtMazluiWkEpR0Mg==, createTime=1782804512168, updateTime=1782804512168, creator=18614031015, updator=18614031015), WebsiteProps(id=1278738063937483676, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1278723867522875769, code=minRunFlag, value=0, createTime=1782804512247, updateTime=1782804512247, creator=18614031015, updator=18614031015), WebsiteProps(id=1278738063652270998, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1278723867522875769, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/oee/EN/file/pic, createTime=1782804512179, updateTime=1782804512179, creator=18614031015, updator=18614031015), WebsiteProps(id=1278738063933289371, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1278723867522875769, code=silenceFlag, value=0, createTime=1782804512246, updateTime=1782804512246, creator=18614031015, updator=18614031015), WebsiteProps(id=1278738063639688085, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1278723867522875769, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1782804512176, updateTime=1782804512176, creator=18614031015, updator=18614031015), WebsiteProps(id=1278738063664853912, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1278723867522875769, code=themeColor, value=null, createTime=1782804512182, updateTime=1782804512182, creator=18614031015, updator=18614031015), WebsiteProps(id=1278738063916512153, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1278723867522875769, code=themeStyle, value=null, createTime=1782804512242, updateTime=1782804512242, creator=18614031015, updator=18614031015)])], journalTitle=光电工程, weixinUrl=null, journalUrl=https://www.oejournal.org/oee, iacademicId=null, status=1, seqNo=null, journalTitleEn=Opto-Electronic Engineering, journalPhotoCn=4Vimkd+qXLWNxtdpr9mFNw==, journalPhotoEn=vAq9s20WLs1ODDfbWq+Gjg==, journalFirstLetter=G, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false, interPubPlatform=, interPubPlatformUrl=null), detailUrlCn=https://castjournals.cast.org.cn/joweb/oee/CN/10.12086/oee.2026.250320, detailUrlEn=https://castjournals.cast.org.cn/joweb/oee/EN/10.12086/oee.2026.250320, pdfUrlCn=https://castjournals.cast.org.cn/joweb/oee/CN/PDF/10.12086/oee.2026.250320, pdfUrlEn=https://castjournals.cast.org.cn/joweb/oee/EN/PDF/10.12086/oee.2026.250320, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1779724800000, fullTextJson=null, articleText=null, reference=null)