用于三维网格分割的CNN-CRF混合推理模型

Youness Abouqora, Omar Herouane, L. Moumoun, T. Gadi
{"title":"用于三维网格分割的CNN-CRF混合推理模型","authors":"Youness Abouqora, Omar Herouane, L. Moumoun, T. Gadi","doi":"10.1109/CiSt49399.2021.9357275","DOIUrl":null,"url":null,"abstract":"Owing to the wide spread of the 3D objects technologies, learning 3D objects labeling and segmentation is becoming one of the most provocative tasks in computer vision and digital multimedia. Recently, convolutional neural network (CNN) has proved itself as a powerful model in segmentation and classification by giving excellent performances. The use of a graphical model such as conditional random field (CRF) contributes further in capturing contextual information and thus improving the segmentation performance. In this paper, we implement a deep architecture in order to segment and label 3D shape parts by considering both spectral and geometric features via a combined framework consisting of a CNN and CRF models. First, low-level features are used to learn deep features using a CNN model, and then formulate the deep CRF model with a CNN-based unary and pairwise potential functions to effectively extract the semantic correlations between adjacent triangles on the mesh. By comparing our results with those from several state-of-the-art, our method shows promising potentials.","PeriodicalId":253233,"journal":{"name":"2020 6th IEEE Congress on Information Science and Technology (CiSt)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"A Hybrid CNN-CRF Inference Models for 3D Mesh Segmentation\",\"authors\":\"Youness Abouqora, Omar Herouane, L. Moumoun, T. Gadi\",\"doi\":\"10.1109/CiSt49399.2021.9357275\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Owing to the wide spread of the 3D objects technologies, learning 3D objects labeling and segmentation is becoming one of the most provocative tasks in computer vision and digital multimedia. Recently, convolutional neural network (CNN) has proved itself as a powerful model in segmentation and classification by giving excellent performances. The use of a graphical model such as conditional random field (CRF) contributes further in capturing contextual information and thus improving the segmentation performance. In this paper, we implement a deep architecture in order to segment and label 3D shape parts by considering both spectral and geometric features via a combined framework consisting of a CNN and CRF models. First, low-level features are used to learn deep features using a CNN model, and then formulate the deep CRF model with a CNN-based unary and pairwise potential functions to effectively extract the semantic correlations between adjacent triangles on the mesh. By comparing our results with those from several state-of-the-art, our method shows promising potentials.\",\"PeriodicalId\":253233,\"journal\":{\"name\":\"2020 6th IEEE Congress on Information Science and Technology (CiSt)\",\"volume\":\"16 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-06-05\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 6th IEEE Congress on Information Science and Technology (CiSt)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/CiSt49399.2021.9357275\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 6th IEEE Congress on Information Science and Technology (CiSt)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CiSt49399.2021.9357275","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

摘要

随着三维物体技术的广泛应用,学习三维物体的标记和分割已成为计算机视觉和数字多媒体领域最具挑战性的课题之一。近年来,卷积神经网络(CNN)以优异的表现证明了自己在分割和分类方面是一种强大的模型。使用图形模型,如条件随机场(CRF)有助于进一步捕获上下文信息,从而提高分割性能。在本文中,我们通过一个由CNN和CRF模型组成的组合框架,通过考虑光谱和几何特征,实现了一个深度架构,以便对3D形状部件进行分割和标记。首先,利用CNN模型利用底层特征学习深层特征,然后利用基于CNN的一元势函数和成对势函数建立深层CRF模型,有效提取网格上相邻三角形之间的语义相关性。通过将我们的结果与几个最先进的结果进行比较,我们的方法显示出很好的潜力。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
A Hybrid CNN-CRF Inference Models for 3D Mesh Segmentation
Owing to the wide spread of the 3D objects technologies, learning 3D objects labeling and segmentation is becoming one of the most provocative tasks in computer vision and digital multimedia. Recently, convolutional neural network (CNN) has proved itself as a powerful model in segmentation and classification by giving excellent performances. The use of a graphical model such as conditional random field (CRF) contributes further in capturing contextual information and thus improving the segmentation performance. In this paper, we implement a deep architecture in order to segment and label 3D shape parts by considering both spectral and geometric features via a combined framework consisting of a CNN and CRF models. First, low-level features are used to learn deep features using a CNN model, and then formulate the deep CRF model with a CNN-based unary and pairwise potential functions to effectively extract the semantic correlations between adjacent triangles on the mesh. By comparing our results with those from several state-of-the-art, our method shows promising potentials.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信