Point cloud geometry compression based on the combination of interlayer residual and IRN concatenated residual

Point clouds have been attracting more and more attentions due to its capability of representing objects precisely, such as autonomous vehicle navigation, VR/AR, cultural heritage protection, etc. However, the enormous amount of data carried in point clouds presents significant challenges for transm...

Full description

Saved in:
Bibliographic Details
Main Authors: Meng Huang, Qian Xu, Wenxuan Xu
Format: Article
Language:English
Published: Elsevier 2025-08-01
Series:Graphical Models
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1524070325000268
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850075234353283072
author Meng Huang
Qian Xu
Wenxuan Xu
author_facet Meng Huang
Qian Xu
Wenxuan Xu
author_sort Meng Huang
collection DOAJ
description Point clouds have been attracting more and more attentions due to its capability of representing objects precisely, such as autonomous vehicle navigation, VR/AR, cultural heritage protection, etc. However, the enormous amount of data carried in point clouds presents significant challenges for transmission and storage. To solve this problem, this dissertation presents a point cloud compression framework based on the combination of interlayer residual and IRN concatenated residual. This paper deployed upsampling design after downsampled point cloud data. It calculates the residuals among point cloud data through downsampling and upsampling processes, consequently, maintains accuracy and reduces errors within the downsampling process. In addition, a novel Inception ResNet-Concatenated Residual Module is designed for maintaining the spatial correlation between layers and blocks. At the same time, it can extract the global and detailed features within point cloud data. Besides, Attention Module is dedicated to enhance the focus on salient features. Respectively compared with the traditional (G-PCC) and the learning point cloud compression method (PCGC v2), this paper lists a series of solid experiments data proving a 70% to 90% and a 6% to 9% BD-Rate gains on 8iVFB and Owlii datasets.
format Article
id doaj-art-79353b5941cd42b78c54b970708f77a3
institution DOAJ
issn 1524-0703
language English
publishDate 2025-08-01
publisher Elsevier
record_format Article
series Graphical Models
spelling doaj-art-79353b5941cd42b78c54b970708f77a32025-08-20T02:46:21ZengElsevierGraphical Models1524-07032025-08-0114010127910.1016/j.gmod.2025.101279Point cloud geometry compression based on the combination of interlayer residual and IRN concatenated residualMeng Huang0Qian Xu1Wenxuan Xu2School of Computer and Control Engineering, Yantai University, No. 30, Qingquan Road, Laishan District, Yantai, 264005, Shandong, ChinaCorresponding author.; School of Computer and Control Engineering, Yantai University, No. 30, Qingquan Road, Laishan District, Yantai, 264005, Shandong, ChinaSchool of Computer and Control Engineering, Yantai University, No. 30, Qingquan Road, Laishan District, Yantai, 264005, Shandong, ChinaPoint clouds have been attracting more and more attentions due to its capability of representing objects precisely, such as autonomous vehicle navigation, VR/AR, cultural heritage protection, etc. However, the enormous amount of data carried in point clouds presents significant challenges for transmission and storage. To solve this problem, this dissertation presents a point cloud compression framework based on the combination of interlayer residual and IRN concatenated residual. This paper deployed upsampling design after downsampled point cloud data. It calculates the residuals among point cloud data through downsampling and upsampling processes, consequently, maintains accuracy and reduces errors within the downsampling process. In addition, a novel Inception ResNet-Concatenated Residual Module is designed for maintaining the spatial correlation between layers and blocks. At the same time, it can extract the global and detailed features within point cloud data. Besides, Attention Module is dedicated to enhance the focus on salient features. Respectively compared with the traditional (G-PCC) and the learning point cloud compression method (PCGC v2), this paper lists a series of solid experiments data proving a 70% to 90% and a 6% to 9% BD-Rate gains on 8iVFB and Owlii datasets.http://www.sciencedirect.com/science/article/pii/S1524070325000268Point cloud geometry compressionInterlayer residualIRNSparse point cloud
spellingShingle Meng Huang
Qian Xu
Wenxuan Xu
Point cloud geometry compression based on the combination of interlayer residual and IRN concatenated residual
Graphical Models
Point cloud geometry compression
Interlayer residual
IRN
Sparse point cloud
title Point cloud geometry compression based on the combination of interlayer residual and IRN concatenated residual
title_full Point cloud geometry compression based on the combination of interlayer residual and IRN concatenated residual
title_fullStr Point cloud geometry compression based on the combination of interlayer residual and IRN concatenated residual
title_full_unstemmed Point cloud geometry compression based on the combination of interlayer residual and IRN concatenated residual
title_short Point cloud geometry compression based on the combination of interlayer residual and IRN concatenated residual
title_sort point cloud geometry compression based on the combination of interlayer residual and irn concatenated residual
topic Point cloud geometry compression
Interlayer residual
IRN
Sparse point cloud
url http://www.sciencedirect.com/science/article/pii/S1524070325000268
work_keys_str_mv AT menghuang pointcloudgeometrycompressionbasedonthecombinationofinterlayerresidualandirnconcatenatedresidual
AT qianxu pointcloudgeometrycompressionbasedonthecombinationofinterlayerresidualandirnconcatenatedresidual
AT wenxuanxu pointcloudgeometrycompressionbasedonthecombinationofinterlayerresidualandirnconcatenatedresidual