S2ANet:结合局部光谱和空间点分组进行点云处理

Q1 Computer Science Virtual Reality Intelligent Hardware Pub Date : 2024-08-01 DOI:10.1016/j.vrih.2023.06.005
Yujie LIU, Xiaorui SUN, Wenbin SHAO, Yafu YUAN
{"title":"S2ANet:结合局部光谱和空间点分组进行点云处理","authors":"Yujie LIU,&nbsp;Xiaorui SUN,&nbsp;Wenbin SHAO,&nbsp;Yafu YUAN","doi":"10.1016/j.vrih.2023.06.005","DOIUrl":null,"url":null,"abstract":"<div><h3>Background</h3><p>Despite the recent progress in 3D point cloud processing using deep convolutional neural networks, the inability to extract local features remains a challenging problem. In addition, existing methods consider only the spatial domain in the feature extraction process.</p></div><div><h3>Methods</h3><p>In this paper, we propose a spectral and spatial aggregation convolutional network (S<sup>2</sup>ANet), which combines spectral and spatial features for point cloud processing. First, we calculate the local frequency of the point cloud in the spectral domain. Then, we use the local frequency to group points and provide a spectral aggregation convolution module to extract the features of the points grouped by the local frequency. We simultaneously extract the local features in the spatial domain to supplement the final features.</p></div><div><h3>Results</h3><p>S<sup>2</sup>ANet was applied in several point cloud analysis tasks; it achieved state-of-the-art classification accuracies of 93.8%, 88.0%, and 83.1% on the ModelNet40, ShapeNetCore, and ScanObjectNN datasets, respectively. For indoor scene segmentation, training and testing were performed on the S3DIS dataset, and the mean intersection over union was 62.4%.</p></div><div><h3>Conclusions</h3><p>The proposed S<sup>2</sup>ANet can effectively capture the local geometric information of point clouds, thereby improving accuracy on various tasks.</p></div>","PeriodicalId":33538,"journal":{"name":"Virtual Reality Intelligent Hardware","volume":"6 4","pages":"Pages 267-279"},"PeriodicalIF":0.0000,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2096579623000360/pdfft?md5=718a7d943dc6468abf44b38521bcc2cb&pid=1-s2.0-S2096579623000360-main.pdf","citationCount":"0","resultStr":"{\"title\":\"S2ANet: Combining local spectral and spatial point grouping for point cloud processing\",\"authors\":\"Yujie LIU,&nbsp;Xiaorui SUN,&nbsp;Wenbin SHAO,&nbsp;Yafu YUAN\",\"doi\":\"10.1016/j.vrih.2023.06.005\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><h3>Background</h3><p>Despite the recent progress in 3D point cloud processing using deep convolutional neural networks, the inability to extract local features remains a challenging problem. In addition, existing methods consider only the spatial domain in the feature extraction process.</p></div><div><h3>Methods</h3><p>In this paper, we propose a spectral and spatial aggregation convolutional network (S<sup>2</sup>ANet), which combines spectral and spatial features for point cloud processing. First, we calculate the local frequency of the point cloud in the spectral domain. Then, we use the local frequency to group points and provide a spectral aggregation convolution module to extract the features of the points grouped by the local frequency. We simultaneously extract the local features in the spatial domain to supplement the final features.</p></div><div><h3>Results</h3><p>S<sup>2</sup>ANet was applied in several point cloud analysis tasks; it achieved state-of-the-art classification accuracies of 93.8%, 88.0%, and 83.1% on the ModelNet40, ShapeNetCore, and ScanObjectNN datasets, respectively. For indoor scene segmentation, training and testing were performed on the S3DIS dataset, and the mean intersection over union was 62.4%.</p></div><div><h3>Conclusions</h3><p>The proposed S<sup>2</sup>ANet can effectively capture the local geometric information of point clouds, thereby improving accuracy on various tasks.</p></div>\",\"PeriodicalId\":33538,\"journal\":{\"name\":\"Virtual Reality Intelligent Hardware\",\"volume\":\"6 4\",\"pages\":\"Pages 267-279\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-08-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.sciencedirect.com/science/article/pii/S2096579623000360/pdfft?md5=718a7d943dc6468abf44b38521bcc2cb&pid=1-s2.0-S2096579623000360-main.pdf\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Virtual Reality Intelligent Hardware\",\"FirstCategoryId\":\"1093\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2096579623000360\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"Computer Science\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Virtual Reality Intelligent Hardware","FirstCategoryId":"1093","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2096579623000360","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"Computer Science","Score":null,"Total":0}
引用次数: 0

摘要

背景尽管最近在使用深度卷积神经网络进行三维点云处理方面取得了进展,但无法提取局部特征仍然是一个具有挑战性的问题。此外,现有方法在特征提取过程中只考虑了空间域。方法在本文中,我们提出了一种光谱和空间聚合卷积网络(S2ANet),它结合了光谱和空间特征,用于点云处理。首先,我们在光谱域计算点云的局部频率。然后,我们利用局部频率对点进行分组,并提供一个光谱聚合卷积模块来提取按局部频率分组的点的特征。我们同时提取了空间域的局部特征,以补充最终特征。结果S2ANet 被应用于多个点云分析任务中;它在 ModelNet40、ShapeNetCore 和 ScanObjectNN 数据集上的分类准确率分别达到了 93.8%、88.0% 和 83.1%,达到了最先进的水平。在室内场景分割方面,在 S3DIS 数据集上进行了训练和测试,平均交集超过联合的比例为 62.4%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
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
S2ANet: Combining local spectral and spatial point grouping for point cloud processing

Background

Despite the recent progress in 3D point cloud processing using deep convolutional neural networks, the inability to extract local features remains a challenging problem. In addition, existing methods consider only the spatial domain in the feature extraction process.

Methods

In this paper, we propose a spectral and spatial aggregation convolutional network (S2ANet), which combines spectral and spatial features for point cloud processing. First, we calculate the local frequency of the point cloud in the spectral domain. Then, we use the local frequency to group points and provide a spectral aggregation convolution module to extract the features of the points grouped by the local frequency. We simultaneously extract the local features in the spatial domain to supplement the final features.

Results

S2ANet was applied in several point cloud analysis tasks; it achieved state-of-the-art classification accuracies of 93.8%, 88.0%, and 83.1% on the ModelNet40, ShapeNetCore, and ScanObjectNN datasets, respectively. For indoor scene segmentation, training and testing were performed on the S3DIS dataset, and the mean intersection over union was 62.4%.

Conclusions

The proposed S2ANet can effectively capture the local geometric information of point clouds, thereby improving accuracy on various tasks.

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
Virtual Reality  Intelligent Hardware
Virtual Reality Intelligent Hardware Computer Science-Computer Graphics and Computer-Aided Design
CiteScore
6.40
自引率
0.00%
发文量
35
审稿时长
12 weeks
期刊最新文献
Co-salient object detection with iterative purification and predictive optimization CURDIS: A template for incremental curve discretization algorithms and its application to conics Mesh representation matters: investigating the influence of different mesh features on perceptual and spatial fidelity of deep 3D morphable models Music-stylized hierarchical dance synthesis with user control Pre-training transformer with dual-branch context content module for table detection in document images
×
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