Point Cloud Quality Assessment Using Cross-correlation of Deep Features

M. Tliba, A. Chetouani, G. Valenzise, F. Dufaux
{"title":"Point Cloud Quality Assessment Using Cross-correlation of Deep Features","authors":"M. Tliba, A. Chetouani, G. Valenzise, F. Dufaux","doi":"10.1145/3552469.3555710","DOIUrl":null,"url":null,"abstract":"3D point clouds have emerged as a preferred format for recent immersive communication systems, due to the six degrees of freedom they offer. The huge data size of point clouds, which consists of both geometry and color information, has motivated the development of efficient compression schemes recently. To support the optimization of these algorithms, adequate and efficient perceptual quality metrics are needed. In this paper we propose a novel end-to-end deep full-reference framework for 3D point cloud quality assessment, considering both the geometry and color information. We use two identical neural networks, based on a residual permutation-invariant architecture, for extracting local features from a sparse set of patches extracted from the point cloud. Afterwards, we measure the cross-correlation between the embedding of pristine and distorted point clouds to quantify the global shift in the features due to visual distortion. The proposed scheme achieves comparable results to state-of-the-art metrics even when a small number of centroids are used, reducing the computational complexity.","PeriodicalId":296389,"journal":{"name":"Proceedings of the 2nd Workshop on Quality of Experience in Visual Multimedia Applications","volume":"43 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 2nd Workshop on Quality of Experience in Visual Multimedia Applications","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3552469.3555710","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 6

Abstract

3D point clouds have emerged as a preferred format for recent immersive communication systems, due to the six degrees of freedom they offer. The huge data size of point clouds, which consists of both geometry and color information, has motivated the development of efficient compression schemes recently. To support the optimization of these algorithms, adequate and efficient perceptual quality metrics are needed. In this paper we propose a novel end-to-end deep full-reference framework for 3D point cloud quality assessment, considering both the geometry and color information. We use two identical neural networks, based on a residual permutation-invariant architecture, for extracting local features from a sparse set of patches extracted from the point cloud. Afterwards, we measure the cross-correlation between the embedding of pristine and distorted point clouds to quantify the global shift in the features due to visual distortion. The proposed scheme achieves comparable results to state-of-the-art metrics even when a small number of centroids are used, reducing the computational complexity.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
基于深度特征互相关的点云质量评价
3D点云已经成为最近沉浸式通信系统的首选格式,因为它们提供了六个自由度。点云数据量巨大,包含几何信息和颜色信息,近年来促使了高效压缩方案的发展。为了支持这些算法的优化,需要足够和有效的感知质量度量。在本文中,我们提出了一个新的端到端深度全参考框架,用于三维点云质量评估,同时考虑几何和颜色信息。我们使用两个相同的神经网络,基于残差置换不变架构,从从点云提取的稀疏补丁集中提取局部特征。然后,我们测量原始点云和扭曲点云嵌入之间的相互关系,以量化由于视觉失真而导致的特征的全局偏移。即使使用少量质心,所提出的方案也能达到与最先进的指标相当的结果,从而降低了计算复杂度。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
From Just Noticeable Differences to Image Quality Estimating the Quality of Experience of Immersive Contents Adversarial Attacks Against Blind Image Quality Assessment Models Point Cloud Quality Assessment Using Cross-correlation of Deep Features Impact of Content on Subjective Quality of Experience Assessment for 3D Video
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1