Ganet: graph attention based Terracotta Warriors point cloud completion network

Abstract Point cloud completion technology is used to address incomplete three-dimensional point cloud data, predicting and reconstructing the original shape and details to achieve virtual restoration. While existing learning-based methods have made significant progress in point cloud completion, th...

Full description

Saved in:
Bibliographic Details
Main Authors: Jian Gao, Yuhe Zhang, Gaoxue Shiqin, Pengbo Zhou, Yue Wen, Guohua Geng
Format: Article
Language:English
Published: SpringerOpen 2024-11-01
Series:Heritage Science
Subjects:
Online Access:https://doi.org/10.1186/s40494-024-01487-9
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846158327488184320
author Jian Gao
Yuhe Zhang
Gaoxue Shiqin
Pengbo Zhou
Yue Wen
Guohua Geng
author_facet Jian Gao
Yuhe Zhang
Gaoxue Shiqin
Pengbo Zhou
Yue Wen
Guohua Geng
author_sort Jian Gao
collection DOAJ
description Abstract Point cloud completion technology is used to address incomplete three-dimensional point cloud data, predicting and reconstructing the original shape and details to achieve virtual restoration. While existing learning-based methods have made significant progress in point cloud completion, they still face challenges when dealing with noise and invisible data. To address these issues, this paper proposes a multi-layer upsampling network based on a graph attention mechanism, called GANet. GANet consists of three main components: (1) feature extraction; (2) seed point generation; (3) State Space Model-based Point Cloud Upsampling Layer. GANet demonstrates exceptional robustness in handling noise and invisible data. To validate the effectiveness of GANet, we applied it to Terracotta Warrior data. The Terracotta Warriors, as important cultural heritage, present a challenging test case due to damage and missing parts caused by prolonged burial and environmental factors. We trained and tested GANet on both the PCN dataset and Terracotta Warrior data, comparing it with several recent learning-based methods. Experimental results show that GANet can effectively reconstruct missing or damaged parts of 3D point clouds, providing more detailed and structurally accurate completion results. These completion models not only validate GANet’s effectiveness but also offer valuable references for cultural heritage restoration work.
format Article
id doaj-art-8c9c0a83b1224faaa9e7d49a2e074d3a
institution Kabale University
issn 2050-7445
language English
publishDate 2024-11-01
publisher SpringerOpen
record_format Article
series Heritage Science
spelling doaj-art-8c9c0a83b1224faaa9e7d49a2e074d3a2024-11-24T12:38:20ZengSpringerOpenHeritage Science2050-74452024-11-0112111410.1186/s40494-024-01487-9Ganet: graph attention based Terracotta Warriors point cloud completion networkJian Gao0Yuhe Zhang1Gaoxue Shiqin2Pengbo Zhou3Yue Wen4Guohua Geng5School of Information Science and Technology, Northwest UniversitySchool of Information Science and Technology, Northwest UniversitySchool of Information Science and Technology, Northwest UniversitySchool of Arts and Communication, Beijing Normal UniversitySchool of law, Wuhan UniversitySchool of Information Science and Technology, Northwest UniversityAbstract Point cloud completion technology is used to address incomplete three-dimensional point cloud data, predicting and reconstructing the original shape and details to achieve virtual restoration. While existing learning-based methods have made significant progress in point cloud completion, they still face challenges when dealing with noise and invisible data. To address these issues, this paper proposes a multi-layer upsampling network based on a graph attention mechanism, called GANet. GANet consists of three main components: (1) feature extraction; (2) seed point generation; (3) State Space Model-based Point Cloud Upsampling Layer. GANet demonstrates exceptional robustness in handling noise and invisible data. To validate the effectiveness of GANet, we applied it to Terracotta Warrior data. The Terracotta Warriors, as important cultural heritage, present a challenging test case due to damage and missing parts caused by prolonged burial and environmental factors. We trained and tested GANet on both the PCN dataset and Terracotta Warrior data, comparing it with several recent learning-based methods. Experimental results show that GANet can effectively reconstruct missing or damaged parts of 3D point clouds, providing more detailed and structurally accurate completion results. These completion models not only validate GANet’s effectiveness but also offer valuable references for cultural heritage restoration work.https://doi.org/10.1186/s40494-024-01487-9Terracotta WarriorsVirtual repairPoint Cloud CompletionDeep learning
spellingShingle Jian Gao
Yuhe Zhang
Gaoxue Shiqin
Pengbo Zhou
Yue Wen
Guohua Geng
Ganet: graph attention based Terracotta Warriors point cloud completion network
Heritage Science
Terracotta Warriors
Virtual repair
Point Cloud Completion
Deep learning
title Ganet: graph attention based Terracotta Warriors point cloud completion network
title_full Ganet: graph attention based Terracotta Warriors point cloud completion network
title_fullStr Ganet: graph attention based Terracotta Warriors point cloud completion network
title_full_unstemmed Ganet: graph attention based Terracotta Warriors point cloud completion network
title_short Ganet: graph attention based Terracotta Warriors point cloud completion network
title_sort ganet graph attention based terracotta warriors point cloud completion network
topic Terracotta Warriors
Virtual repair
Point Cloud Completion
Deep learning
url https://doi.org/10.1186/s40494-024-01487-9
work_keys_str_mv AT jiangao ganetgraphattentionbasedterracottawarriorspointcloudcompletionnetwork
AT yuhezhang ganetgraphattentionbasedterracottawarriorspointcloudcompletionnetwork
AT gaoxueshiqin ganetgraphattentionbasedterracottawarriorspointcloudcompletionnetwork
AT pengbozhou ganetgraphattentionbasedterracottawarriorspointcloudcompletionnetwork
AT yuewen ganetgraphattentionbasedterracottawarriorspointcloudcompletionnetwork
AT guohuageng ganetgraphattentionbasedterracottawarriorspointcloudcompletionnetwork