Point Cloud Geometry Prediction Across Spatial Scale using Deep Learning

Anique Akhtar, Wen Gao, Xianguo Zhang, Li Li, Zhu Li, Shan Liu
{"title":"Point Cloud Geometry Prediction Across Spatial Scale using Deep Learning","authors":"Anique Akhtar, Wen Gao, Xianguo Zhang, Li Li, Zhu Li, Shan Liu","doi":"10.1109/VCIP49819.2020.9301804","DOIUrl":null,"url":null,"abstract":"A point cloud is a 3D data representation that is becoming increasingly popular. Due to the large size of a point cloud, the transmission of point cloud is not feasible without compression. However, the current point cloud lossy compression and processing techniques suffer from quantization loss which results in a coarser sub-sampled representation of point cloud. In this paper, we solve the problem of points lost during voxelization by performing geometry prediction across spatial scale using deep learning architecture. We perform an octree-type upsampling of point cloud geometry where each voxel point is divided into 8 sub-voxel points and their occupancy is predicted by our network. This way we obtain a denser representation of the point cloud while minimizing the losses with respect to the ground truth. We utilize sparse tensors with sparse convolutions by using Minkowski Engine with a UNet like network equipped with inception-residual network blocks. Our results show that our geometry prediction scheme can significantly improve the PSNR of a point cloud, therefore, making it an essential post-processing scheme for the compression-transmission pipeline. This solution can serve as a crucial prediction tool across scale for point cloud compression, as well as display adaptation.","PeriodicalId":431880,"journal":{"name":"2020 IEEE International Conference on Visual Communications and Image Processing (VCIP)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"11","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 IEEE International Conference on Visual Communications and Image Processing (VCIP)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/VCIP49819.2020.9301804","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 11

Abstract

A point cloud is a 3D data representation that is becoming increasingly popular. Due to the large size of a point cloud, the transmission of point cloud is not feasible without compression. However, the current point cloud lossy compression and processing techniques suffer from quantization loss which results in a coarser sub-sampled representation of point cloud. In this paper, we solve the problem of points lost during voxelization by performing geometry prediction across spatial scale using deep learning architecture. We perform an octree-type upsampling of point cloud geometry where each voxel point is divided into 8 sub-voxel points and their occupancy is predicted by our network. This way we obtain a denser representation of the point cloud while minimizing the losses with respect to the ground truth. We utilize sparse tensors with sparse convolutions by using Minkowski Engine with a UNet like network equipped with inception-residual network blocks. Our results show that our geometry prediction scheme can significantly improve the PSNR of a point cloud, therefore, making it an essential post-processing scheme for the compression-transmission pipeline. This solution can serve as a crucial prediction tool across scale for point cloud compression, as well as display adaptation.
利用深度学习跨空间尺度的点云几何预测
点云是一种越来越流行的3D数据表示。由于点云的体积较大,不进行压缩传输是不可行的。然而,目前的点云有损压缩和处理技术存在量化损失,导致点云的子采样表示较为粗糙。在本文中,我们通过使用深度学习架构跨空间尺度进行几何预测来解决体素化过程中丢失点的问题。我们执行点云几何的八叉树式上采样,其中每个体素点被划分为8个子体素点,并由我们的网络预测它们的占用情况。通过这种方式,我们获得了点云的更密集的表示,同时最小化了相对于地面真值的损失。我们通过使用Minkowski引擎和带有初始-残差网络块的UNet类网络来利用稀疏卷积的稀疏张量。结果表明,我们的几何预测方案可以显著提高点云的PSNR,因此,使其成为压缩传输管道必不可少的后处理方案。该解决方案可作为点云压缩和显示适应跨尺度的关键预测工具。
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 求助全文
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