3D Model Retrieval Based on Representative Views

3D model retrieval based on representative views was proposed. On the view representation of the 3D model, in order to fully represent the model and reduce redundant information, we firstly adopt Light Field Descriptor (LFD) to generate 2D views, and then use K-MEANS to get representative views from...

Full description

Saved in:
Bibliographic Details
Main Authors: DING Bo, TANG Lei, HE Yong jun, YU Jun
Format: Article
Language:zho
Published: Harbin University of Science and Technology Publications 2021-12-01
Series:Journal of Harbin University of Science and Technology
Subjects:
Online Access:https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=2030
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850055435115036672
author DING Bo
TANG Lei
HE Yong jun
YU Jun
author_facet DING Bo
TANG Lei
HE Yong jun
YU Jun
author_sort DING Bo
collection DOAJ
description 3D model retrieval based on representative views was proposed. On the view representation of the 3D model, in order to fully represent the model and reduce redundant information, we firstly adopt Light Field Descriptor (LFD) to generate 2D views, and then use K-MEANS to get representative views from the 2D views. Next, a Convolution Neural Network (CNN) is adopted to extract the view feature and classify. At the same time, a similarity metrics supporting multiple query method is proposed to realize model retrieval with sketches, pictures or 3D models as input. Results on ModelNet40 showed that the proposed method could achieve an accuracy of 100% for part of models with distinct features
format Article
id doaj-art-7a03803fd9c74ab78cb3e8048bc5660e
institution DOAJ
issn 1007-2683
language zho
publishDate 2021-12-01
publisher Harbin University of Science and Technology Publications
record_format Article
series Journal of Harbin University of Science and Technology
spelling doaj-art-7a03803fd9c74ab78cb3e8048bc5660e2025-08-20T02:51:59ZzhoHarbin University of Science and Technology PublicationsJournal of Harbin University of Science and Technology1007-26832021-12-012606182310.15938/j.jhust.2021.06.0033D Model Retrieval Based on Representative ViewsDING Bo0TANG Lei1HE Yong jun2YU Jun3School of Computer Science and Technology, Harbin University of Science and Technology, Harbin 150080, ChinaSchool of Computer Science and Technology, Harbin University of Science and Technology, Harbin 150080, ChinaSchool of Computer Science and Technology, Harbin University of Science and Technology, Harbin 150080, ChinaSchool of Automation, Harbin University of Science and Technology, Harbin 150080, China3D model retrieval based on representative views was proposed. On the view representation of the 3D model, in order to fully represent the model and reduce redundant information, we firstly adopt Light Field Descriptor (LFD) to generate 2D views, and then use K-MEANS to get representative views from the 2D views. Next, a Convolution Neural Network (CNN) is adopted to extract the view feature and classify. At the same time, a similarity metrics supporting multiple query method is proposed to realize model retrieval with sketches, pictures or 3D models as input. Results on ModelNet40 showed that the proposed method could achieve an accuracy of 100% for part of models with distinct featureshttps://hlgxb.hrbust.edu.cn/#/digest?ArticleID=20303d model retrievalrepresentative viewsconvolutional neural networkk-means
spellingShingle DING Bo
TANG Lei
HE Yong jun
YU Jun
3D Model Retrieval Based on Representative Views
Journal of Harbin University of Science and Technology
3d model retrieval
representative views
convolutional neural network
k-means
title 3D Model Retrieval Based on Representative Views
title_full 3D Model Retrieval Based on Representative Views
title_fullStr 3D Model Retrieval Based on Representative Views
title_full_unstemmed 3D Model Retrieval Based on Representative Views
title_short 3D Model Retrieval Based on Representative Views
title_sort 3d model retrieval based on representative views
topic 3d model retrieval
representative views
convolutional neural network
k-means
url https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=2030
work_keys_str_mv AT dingbo 3dmodelretrievalbasedonrepresentativeviews
AT tanglei 3dmodelretrievalbasedonrepresentativeviews
AT heyongjun 3dmodelretrievalbasedonrepresentativeviews
AT yujun 3dmodelretrievalbasedonrepresentativeviews