C2SPoint: A classification-to-saliency network for point cloud saliency detection

Jiang, Zhaoyi; Ding, Luyun; Tam, Gary; Song, Chao; Li, Frederick W.B.; Yang, Bailin

doi:10.1016/j.cag.2023.07.003

Journal article 239 views 130 downloads

C2SPoint: A classification-to-saliency network for point cloud saliency detection

Zhaoyi Jiang

, Luyun Ding, Gary Tam

, Chao Song, Frederick W.B. Li, Bailin Yang

Computers and Graphics, Volume: 115, Pages: 274 - 284

Swansea University Author: Gary Tam

PDF | Accepted Manuscript

For the purpose of Open Access the author has applied a CC BY copyright licence to any Author Accepted Manuscript version arising from this submission.
Download (5.2MB)

Check full text

DOI (Published version): 10.1016/j.cag.2023.07.003

Abstract

Point cloud saliency detection is an important technique that support downstream tasks in 3D graphics and vision, like 3D model simplification, compression, reconstruction and viewpoint selection. Existing approaches often rely on hand-crafted features and are only applicable to specific datasets. I...

Full description

Published in:	Computers and Graphics
ISSN:	0097-8493 0097-8493
Published:	Elsevier BV 2023
Online Access:	Check full text
URI:	https://cronfa.swan.ac.uk/Record/cronfa63869
Tags:	Add Tag No Tags, Be the first to tag this record!

first_indexed	2023-07-12T10:34:39Z
last_indexed	2023-07-12T10:34:39Z
id	cronfa63869
recordtype	SURis
fullrecord	<?xml version="1.0" encoding="utf-8"?><rfc1807 xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema"><bib-version>v2</bib-version><id>63869</id><entry>2023-07-12</entry><title>C2SPoint: A classification-to-saliency network for point cloud saliency detection</title><swanseaauthors><author><sid>e75a68e11a20e5f1da94ee6e28ff5e76</sid><ORCID>0000-0001-7387-5180</ORCID><firstname>Gary</firstname><surname>Tam</surname><name>Gary Tam</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2023-07-12</date><deptcode>SCS</deptcode><abstract>Point cloud saliency detection is an important technique that support downstream tasks in 3D graphics and vision, like 3D model simplification, compression, reconstruction and viewpoint selection. Existing approaches often rely on hand-crafted features and are only applicable to specific datasets. In this paper, we propose a novel weakly supervised classification network, called C2SPoint, which directly performs saliency detection on the point clouds. Unlike previous methods that require per-point saliency annotations, C2SPoint only requires category labels of the point clouds during training. The network consists of two branches: a Classification branch and a Saliency branch. The former branch is composed of two Adaptive Set Abstraction layers for feature extraction and a Saliency Transform layer for learning saliency knowledge from the classification network. The latter branch introduces a multi-scale point-cluster similarity matrix for propagating the cluster saliency to each point within it, resulting in the prediction of point-level saliency. Experimental results demonstrate the effectiveness of our method in point cloud saliency detection, with improvements of 2% in both AUC and NSS compared to state-of-the-art methods.</abstract><type>Journal Article</type><journal>Computers and Graphics</journal><volume>115</volume><journalNumber/><paginationStart>274</paginationStart><paginationEnd>284</paginationEnd><publisher>Elsevier BV</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>0097-8493</issnPrint><issnElectronic>0097-8493</issnElectronic><keywords>Point cloud saliency detection, Weakly-supervised learning, Learning features, PointNet++</keywords><publishedDay>31</publishedDay><publishedMonth>10</publishedMonth><publishedYear>2023</publishedYear><publishedDate>2023-10-31</publishedDate><doi>10.1016/j.cag.2023.07.003</doi><url>http://dx.doi.org/10.1016/j.cag.2023.07.003</url><notes/><college>COLLEGE NANME</college><department>Computer Science</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>SCS</DepartmentCode><institution>Swansea University</institution><apcterm/><funders>This research was partially supported by Zhejiang Province Natural Science Foundation No. LY21F020013, LY22F020013, the National Natural Science Foundation of China No. 62172366. Gary Tam is supported by the Royal Society grant IEC/NSFC/211159. For the purpose of Open Access the author has applied a CC BY copyright licence to any Author Accepted Manuscript version arising from this submission.</funders><projectreference/><lastEdited>2023-09-22T16:14:19.6334130</lastEdited><Created>2023-07-12T11:30:56.1296100</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>Zhaoyi</firstname><surname>Jiang</surname><orcid>0000-0001-5347-7935</orcid><order>1</order></author><author><firstname>Luyun</firstname><surname>Ding</surname><order>2</order></author><author><firstname>Gary</firstname><surname>Tam</surname><orcid>0000-0001-7387-5180</orcid><order>3</order></author><author><firstname>Chao</firstname><surname>Song</surname><order>4</order></author><author><firstname>Frederick W.B.</firstname><surname>Li</surname><order>5</order></author><author><firstname>Bailin</firstname><surname>Yang</surname><order>6</order></author></authors><documents><document><filename>63869__28149__18185e61da45490dbef41e3646a14a60.pdf</filename><originalFilename>63869.pdf</originalFilename><uploaded>2023-07-19T14:19:01.6357747</uploaded><type>Output</type><contentLength>5447949</contentLength><contentType>application/pdf</contentType><version>Accepted Manuscript</version><cronfaStatus>true</cronfaStatus><documentNotes>For the purpose of Open Access the author has applied a CC BY copyright licence to any Author Accepted Manuscript version arising from this submission.</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language></document></documents><OutputDurs/></rfc1807>
spelling	v2 63869 2023-07-12 C2SPoint: A classification-to-saliency network for point cloud saliency detection e75a68e11a20e5f1da94ee6e28ff5e76 0000-0001-7387-5180 Gary Tam Gary Tam true false 2023-07-12 SCS Point cloud saliency detection is an important technique that support downstream tasks in 3D graphics and vision, like 3D model simplification, compression, reconstruction and viewpoint selection. Existing approaches often rely on hand-crafted features and are only applicable to specific datasets. In this paper, we propose a novel weakly supervised classification network, called C2SPoint, which directly performs saliency detection on the point clouds. Unlike previous methods that require per-point saliency annotations, C2SPoint only requires category labels of the point clouds during training. The network consists of two branches: a Classification branch and a Saliency branch. The former branch is composed of two Adaptive Set Abstraction layers for feature extraction and a Saliency Transform layer for learning saliency knowledge from the classification network. The latter branch introduces a multi-scale point-cluster similarity matrix for propagating the cluster saliency to each point within it, resulting in the prediction of point-level saliency. Experimental results demonstrate the effectiveness of our method in point cloud saliency detection, with improvements of 2% in both AUC and NSS compared to state-of-the-art methods. Journal Article Computers and Graphics 115 274 284 Elsevier BV 0097-8493 0097-8493 Point cloud saliency detection, Weakly-supervised learning, Learning features, PointNet++ 31 10 2023 2023-10-31 10.1016/j.cag.2023.07.003 http://dx.doi.org/10.1016/j.cag.2023.07.003 COLLEGE NANME Computer Science COLLEGE CODE SCS Swansea University This research was partially supported by Zhejiang Province Natural Science Foundation No. LY21F020013, LY22F020013, the National Natural Science Foundation of China No. 62172366. Gary Tam is supported by the Royal Society grant IEC/NSFC/211159. For the purpose of Open Access the author has applied a CC BY copyright licence to any Author Accepted Manuscript version arising from this submission. 2023-09-22T16:14:19.6334130 2023-07-12T11:30:56.1296100 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Zhaoyi Jiang 0000-0001-5347-7935 1 Luyun Ding 2 Gary Tam 0000-0001-7387-5180 3 Chao Song 4 Frederick W.B. Li 5 Bailin Yang 6 63869__28149__18185e61da45490dbef41e3646a14a60.pdf 63869.pdf 2023-07-19T14:19:01.6357747 Output 5447949 application/pdf Accepted Manuscript true For the purpose of Open Access the author has applied a CC BY copyright licence to any Author Accepted Manuscript version arising from this submission. true eng
title	C2SPoint: A classification-to-saliency network for point cloud saliency detection
spellingShingle	C2SPoint: A classification-to-saliency network for point cloud saliency detection Gary Tam
title_short	C2SPoint: A classification-to-saliency network for point cloud saliency detection
title_full	C2SPoint: A classification-to-saliency network for point cloud saliency detection
title_fullStr	C2SPoint: A classification-to-saliency network for point cloud saliency detection
title_full_unstemmed	C2SPoint: A classification-to-saliency network for point cloud saliency detection
title_sort	C2SPoint: A classification-to-saliency network for point cloud saliency detection
author_id_str_mv	e75a68e11a20e5f1da94ee6e28ff5e76
author_id_fullname_str_mv	e75a68e11a20e5f1da94ee6e28ff5e76_***_Gary Tam
author	Gary Tam
author2	Zhaoyi Jiang Luyun Ding Gary Tam Chao Song Frederick W.B. Li Bailin Yang
format	Journal article
container_title	Computers and Graphics
container_volume	115
container_start_page	274
publishDate	2023
institution	Swansea University
issn	0097-8493 0097-8493
doi_str_mv	10.1016/j.cag.2023.07.003
publisher	Elsevier BV
college_str	Faculty of Science and Engineering
hierarchytype
hierarchy_top_id	facultyofscienceandengineering
hierarchy_top_title	Faculty of Science and Engineering
hierarchy_parent_id	facultyofscienceandengineering
hierarchy_parent_title	Faculty of Science and Engineering
department_str	School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
url	http://dx.doi.org/10.1016/j.cag.2023.07.003
document_store_str	1
active_str	0
description	Point cloud saliency detection is an important technique that support downstream tasks in 3D graphics and vision, like 3D model simplification, compression, reconstruction and viewpoint selection. Existing approaches often rely on hand-crafted features and are only applicable to specific datasets. In this paper, we propose a novel weakly supervised classification network, called C2SPoint, which directly performs saliency detection on the point clouds. Unlike previous methods that require per-point saliency annotations, C2SPoint only requires category labels of the point clouds during training. The network consists of two branches: a Classification branch and a Saliency branch. The former branch is composed of two Adaptive Set Abstraction layers for feature extraction and a Saliency Transform layer for learning saliency knowledge from the classification network. The latter branch introduces a multi-scale point-cluster similarity matrix for propagating the cluster saliency to each point within it, resulting in the prediction of point-level saliency. Experimental results demonstrate the effectiveness of our method in point cloud saliency detection, with improvements of 2% in both AUC and NSS compared to state-of-the-art methods.
published_date	2023-10-31T16:14:18Z
_version_	1777751198085939200
score	11.012678

C2SPoint: A classification-to-saliency network for point cloud saliency detection

Similar Items