No Cover Image

Journal article 385 views 174 downloads

Denoising-While-Completing Network (DWCNet): Robust point cloud completion under corruption

Keneni Tesema Orcid Logo, Lyndon Hill, Mark Jones Orcid Logo, Gary Tam Orcid Logo

Computers & Graphics, Volume: 132, Start page: 104401

Swansea University Authors: Keneni Tesema Orcid Logo, Mark Jones Orcid Logo, Gary Tam Orcid Logo

  • 69951.VOR.pdf

    PDF | Version of Record

    © 2025 The Authors. This is an open access article distributed under the terms of the Creative Commons CC-BY license.

    Download (10.01MB)

Check full text

DOI (Published version): 10.1016/j.cag.2025.104401

Abstract

Point cloud completion is crucial for 3D computer vision tasks in autonomous driving, augmented reality, and robotics. However, obtaining clean and complete point clouds from real-world environments is challenging due to noise and occlusions. Consequently, most existing completion networks – trained...

Full description

Published in: Computers & Graphics
ISSN: 0097-8493 1873-768
Published: Elsevier BV 2025
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa69951
first_indexed 2025-07-13T16:01:40Z
last_indexed 2025-09-12T09:59:24Z
id cronfa69951
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2025-09-11T09:26:34.2709817</datestamp><bib-version>v2</bib-version><id>69951</id><entry>2025-07-13</entry><title>Denoising-While-Completing Network (DWCNet): Robust point cloud completion under corruption</title><swanseaauthors><author><sid>565d5e98f266077e36258ac9c10b2a80</sid><ORCID>0009-0003-1247-2435</ORCID><firstname>Keneni</firstname><surname>Tesema</surname><name>Keneni Tesema</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>2e1030b6e14fc9debd5d5ae7cc335562</sid><ORCID>0000-0001-8991-1190</ORCID><firstname>Mark</firstname><surname>Jones</surname><name>Mark Jones</name><active>true</active><ethesisStudent>false</ethesisStudent></author><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>2025-07-13</date><abstract>Point cloud completion is crucial for 3D computer vision tasks in autonomous driving, augmented reality, and robotics. However, obtaining clean and complete point clouds from real-world environments is challenging due to noise and occlusions. Consequently, most existing completion networks &#x2013; trained on synthetic data &#x2013; struggle with real-world degradations. In this work, we tackle the problem of completing and denoising highly corrupted partial point clouds affected by multiple simultaneous degradations. To benchmark robustness, we introduce the Corrupted Point Cloud Completion Dataset (CPCCD), which highlights the limitations of current methods under diverse corruptions. Building on these insights, we propose DWCNet (Denoising-While-Completing Network), a completion framework enhanced with a Noise Management Module (NMM) that leverages contrastive learning and self-attention to suppress noise and model structural relationships. DWCNet achieves state-of-the-art performance on both clean and corrupted, synthetic and real-world datasets. The dataset and code will be publicly available at https://github.com/keneniwt/DWCNET-Robust-Point-Cloud-Completion-against-Corruptions.</abstract><type>Journal Article</type><journal>Computers &amp; Graphics</journal><volume>132</volume><journalNumber/><paginationStart>104401</paginationStart><paginationEnd/><publisher>Elsevier BV</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>0097-8493</issnPrint><issnElectronic>1873-768</issnElectronic><keywords>Point cloud completion; Point cloud denoising; Robustness benchmark dataset</keywords><publishedDay>1</publishedDay><publishedMonth>11</publishedMonth><publishedYear>2025</publishedYear><publishedDate>2025-11-01</publishedDate><doi>10.1016/j.cag.2025.104401</doi><url/><notes/><college>COLLEGE NANME</college><CollegeCode>COLLEGE CODE</CollegeCode><institution>Swansea University</institution><apcterm>SU Library paid the OA fee (TA Institutional Deal)</apcterm><funders>This work was funded by EPSRC, United Kingdom grant number EP/S021892/1 and Beam (Previously Vaarst) (beam.global). Tam is partially supported by a Royal Society, United Kingdom fund IEC/NSFC/211159.</funders><projectreference/><lastEdited>2025-09-11T09:26:34.2709817</lastEdited><Created>2025-07-13T16:00:14.1685678</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>Keneni</firstname><surname>Tesema</surname><orcid>0009-0003-1247-2435</orcid><order>1</order></author><author><firstname>Lyndon</firstname><surname>Hill</surname><order>2</order></author><author><firstname>Mark</firstname><surname>Jones</surname><orcid>0000-0001-8991-1190</orcid><order>3</order></author><author><firstname>Gary</firstname><surname>Tam</surname><orcid>0000-0001-7387-5180</orcid><order>4</order></author></authors><documents><document><filename>69951__35074__476a50c5792a458aa853b39257dd4c7d.pdf</filename><originalFilename>69951.VOR.pdf</originalFilename><uploaded>2025-09-11T09:24:04.3903629</uploaded><type>Output</type><contentLength>10492104</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>&#xA9; 2025 The Authors. This is an open access article distributed under the terms of the Creative Commons CC-BY license.</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>http://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling 2025-09-11T09:26:34.2709817 v2 69951 2025-07-13 Denoising-While-Completing Network (DWCNet): Robust point cloud completion under corruption 565d5e98f266077e36258ac9c10b2a80 0009-0003-1247-2435 Keneni Tesema Keneni Tesema true false 2e1030b6e14fc9debd5d5ae7cc335562 0000-0001-8991-1190 Mark Jones Mark Jones true false e75a68e11a20e5f1da94ee6e28ff5e76 0000-0001-7387-5180 Gary Tam Gary Tam true false 2025-07-13 Point cloud completion is crucial for 3D computer vision tasks in autonomous driving, augmented reality, and robotics. However, obtaining clean and complete point clouds from real-world environments is challenging due to noise and occlusions. Consequently, most existing completion networks – trained on synthetic data – struggle with real-world degradations. In this work, we tackle the problem of completing and denoising highly corrupted partial point clouds affected by multiple simultaneous degradations. To benchmark robustness, we introduce the Corrupted Point Cloud Completion Dataset (CPCCD), which highlights the limitations of current methods under diverse corruptions. Building on these insights, we propose DWCNet (Denoising-While-Completing Network), a completion framework enhanced with a Noise Management Module (NMM) that leverages contrastive learning and self-attention to suppress noise and model structural relationships. DWCNet achieves state-of-the-art performance on both clean and corrupted, synthetic and real-world datasets. The dataset and code will be publicly available at https://github.com/keneniwt/DWCNET-Robust-Point-Cloud-Completion-against-Corruptions. Journal Article Computers & Graphics 132 104401 Elsevier BV 0097-8493 1873-768 Point cloud completion; Point cloud denoising; Robustness benchmark dataset 1 11 2025 2025-11-01 10.1016/j.cag.2025.104401 COLLEGE NANME COLLEGE CODE Swansea University SU Library paid the OA fee (TA Institutional Deal) This work was funded by EPSRC, United Kingdom grant number EP/S021892/1 and Beam (Previously Vaarst) (beam.global). Tam is partially supported by a Royal Society, United Kingdom fund IEC/NSFC/211159. 2025-09-11T09:26:34.2709817 2025-07-13T16:00:14.1685678 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Keneni Tesema 0009-0003-1247-2435 1 Lyndon Hill 2 Mark Jones 0000-0001-8991-1190 3 Gary Tam 0000-0001-7387-5180 4 69951__35074__476a50c5792a458aa853b39257dd4c7d.pdf 69951.VOR.pdf 2025-09-11T09:24:04.3903629 Output 10492104 application/pdf Version of Record true © 2025 The Authors. This is an open access article distributed under the terms of the Creative Commons CC-BY license. true eng http://creativecommons.org/licenses/by/4.0/
title Denoising-While-Completing Network (DWCNet): Robust point cloud completion under corruption
spellingShingle Denoising-While-Completing Network (DWCNet): Robust point cloud completion under corruption
Keneni Tesema
Mark Jones
Gary Tam
title_short Denoising-While-Completing Network (DWCNet): Robust point cloud completion under corruption
title_full Denoising-While-Completing Network (DWCNet): Robust point cloud completion under corruption
title_fullStr Denoising-While-Completing Network (DWCNet): Robust point cloud completion under corruption
title_full_unstemmed Denoising-While-Completing Network (DWCNet): Robust point cloud completion under corruption
title_sort Denoising-While-Completing Network (DWCNet): Robust point cloud completion under corruption
author_id_str_mv 565d5e98f266077e36258ac9c10b2a80
2e1030b6e14fc9debd5d5ae7cc335562
e75a68e11a20e5f1da94ee6e28ff5e76
author_id_fullname_str_mv 565d5e98f266077e36258ac9c10b2a80_***_Keneni Tesema
2e1030b6e14fc9debd5d5ae7cc335562_***_Mark Jones
e75a68e11a20e5f1da94ee6e28ff5e76_***_Gary Tam
author Keneni Tesema
Mark Jones
Gary Tam
author2 Keneni Tesema
Lyndon Hill
Mark Jones
Gary Tam
format Journal article
container_title Computers & Graphics
container_volume 132
container_start_page 104401
publishDate 2025
institution Swansea University
issn 0097-8493
1873-768
doi_str_mv 10.1016/j.cag.2025.104401
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
document_store_str 1
active_str 0
description Point cloud completion is crucial for 3D computer vision tasks in autonomous driving, augmented reality, and robotics. However, obtaining clean and complete point clouds from real-world environments is challenging due to noise and occlusions. Consequently, most existing completion networks – trained on synthetic data – struggle with real-world degradations. In this work, we tackle the problem of completing and denoising highly corrupted partial point clouds affected by multiple simultaneous degradations. To benchmark robustness, we introduce the Corrupted Point Cloud Completion Dataset (CPCCD), which highlights the limitations of current methods under diverse corruptions. Building on these insights, we propose DWCNet (Denoising-While-Completing Network), a completion framework enhanced with a Noise Management Module (NMM) that leverages contrastive learning and self-attention to suppress noise and model structural relationships. DWCNet achieves state-of-the-art performance on both clean and corrupted, synthetic and real-world datasets. The dataset and code will be publicly available at https://github.com/keneniwt/DWCNET-Robust-Point-Cloud-Completion-against-Corruptions.
published_date 2025-11-01T05:29:33Z
_version_ 1851097951699468288
score 11.089386

Similar Items