Point cloud completion method, system and application

Point cloud completion method, system and application

The invention belongs to the technical field of computer vision, and discloses a point cloud completion method and system and application, and the method comprises the steps: firstly constructing an input point cloud prior information extraction unit; constructing an intermediate point cloud prior i...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: LI JIAOJIAO, CAO KAILANG, WANG YANGLI, SONG RUI, ZHANG YUHANG, LI YUNSONG, XIA YAQI
Format: Patent
Sprache:chi ; eng
Schlagworte:
CALCULATING
COMPUTING
COUNTING
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator LI JIAOJIAO
CAO KAILANG
WANG YANGLI
SONG RUI
ZHANG YUHANG
LI YUNSONG
XIA YAQI
description The invention belongs to the technical field of computer vision, and discloses a point cloud completion method and system and application, and the method comprises the steps: firstly constructing an input point cloud prior information extraction unit; constructing an intermediate point cloud prior information extraction unit; constructing a point cloud refinement unit; judging whether the number of the output point cloud points meets the requirement or not, and if not, constructing the point cloud refining unit again until the requirement is met; generating a training set to train the point cloud completion model; and finally, complementing the incomplete point cloud by using the trained model. According to the point cloud completion method provided by the invention, the incomplete input point cloud and the general point cloud are fully utilized to complement the object shape prior information provided by the output point cloud of the network, and the prior information is integrated and processed through the
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN113052955A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN113052955A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN113052955A3</originalsourceid><addsrcrecordid>eNrjZDANyM_MK1FIzskvTVFIzs8tyEktyczPU8hNLcnIT9FRKK4sLknNVUjMS1FILCjIyUxOBEnzMLCmJeYUp_JCaW4GRTfXEGcP3dSC_PjU4oLE5NS81JJ4Zz9DQ2MDUyNLU1NHY2LUAAB2QS1O</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Point cloud completion method, system and application</title><source>esp@cenet</source><creator>LI JIAOJIAO ; CAO KAILANG ; WANG YANGLI ; SONG RUI ; ZHANG YUHANG ; LI YUNSONG ; XIA YAQI</creator><creatorcontrib>LI JIAOJIAO ; CAO KAILANG ; WANG YANGLI ; SONG RUI ; ZHANG YUHANG ; LI YUNSONG ; XIA YAQI</creatorcontrib><description>The invention belongs to the technical field of computer vision, and discloses a point cloud completion method and system and application, and the method comprises the steps: firstly constructing an input point cloud prior information extraction unit; constructing an intermediate point cloud prior information extraction unit; constructing a point cloud refinement unit; judging whether the number of the output point cloud points meets the requirement or not, and if not, constructing the point cloud refining unit again until the requirement is met; generating a training set to train the point cloud completion model; and finally, complementing the incomplete point cloud by using the trained model. According to the point cloud completion method provided by the invention, the incomplete input point cloud and the general point cloud are fully utilized to complement the object shape prior information provided by the output point cloud of the network, and the prior information is integrated and processed through the</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTING ; COUNTING ; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ; PHYSICS</subject><creationdate>2021</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20210629&amp;DB=EPODOC&amp;CC=CN&amp;NR=113052955A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76289</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20210629&amp;DB=EPODOC&amp;CC=CN&amp;NR=113052955A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>LI JIAOJIAO</creatorcontrib><creatorcontrib>CAO KAILANG</creatorcontrib><creatorcontrib>WANG YANGLI</creatorcontrib><creatorcontrib>SONG RUI</creatorcontrib><creatorcontrib>ZHANG YUHANG</creatorcontrib><creatorcontrib>LI YUNSONG</creatorcontrib><creatorcontrib>XIA YAQI</creatorcontrib><title>Point cloud completion method, system and application</title><description>The invention belongs to the technical field of computer vision, and discloses a point cloud completion method and system and application, and the method comprises the steps: firstly constructing an input point cloud prior information extraction unit; constructing an intermediate point cloud prior information extraction unit; constructing a point cloud refinement unit; judging whether the number of the output point cloud points meets the requirement or not, and if not, constructing the point cloud refining unit again until the requirement is met; generating a training set to train the point cloud completion model; and finally, complementing the incomplete point cloud by using the trained model. According to the point cloud completion method provided by the invention, the incomplete input point cloud and the general point cloud are fully utilized to complement the object shape prior information provided by the output point cloud of the network, and the prior information is integrated and processed through the</description><subject>CALCULATING</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2021</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZDANyM_MK1FIzskvTVFIzs8tyEktyczPU8hNLcnIT9FRKK4sLknNVUjMS1FILCjIyUxOBEnzMLCmJeYUp_JCaW4GRTfXEGcP3dSC_PjU4oLE5NS81JJ4Zz9DQ2MDUyNLU1NHY2LUAAB2QS1O</recordid><startdate>20210629</startdate><enddate>20210629</enddate><creator>LI JIAOJIAO</creator><creator>CAO KAILANG</creator><creator>WANG YANGLI</creator><creator>SONG RUI</creator><creator>ZHANG YUHANG</creator><creator>LI YUNSONG</creator><creator>XIA YAQI</creator><scope>EVB</scope></search><sort><creationdate>20210629</creationdate><title>Point cloud completion method, system and application</title><author>LI JIAOJIAO ; CAO KAILANG ; WANG YANGLI ; SONG RUI ; ZHANG YUHANG ; LI YUNSONG ; XIA YAQI</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN113052955A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2021</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>LI JIAOJIAO</creatorcontrib><creatorcontrib>CAO KAILANG</creatorcontrib><creatorcontrib>WANG YANGLI</creatorcontrib><creatorcontrib>SONG RUI</creatorcontrib><creatorcontrib>ZHANG YUHANG</creatorcontrib><creatorcontrib>LI YUNSONG</creatorcontrib><creatorcontrib>XIA YAQI</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>LI JIAOJIAO</au><au>CAO KAILANG</au><au>WANG YANGLI</au><au>SONG RUI</au><au>ZHANG YUHANG</au><au>LI YUNSONG</au><au>XIA YAQI</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Point cloud completion method, system and application</title><date>2021-06-29</date><risdate>2021</risdate><abstract>The invention belongs to the technical field of computer vision, and discloses a point cloud completion method and system and application, and the method comprises the steps: firstly constructing an input point cloud prior information extraction unit; constructing an intermediate point cloud prior information extraction unit; constructing a point cloud refinement unit; judging whether the number of the output point cloud points meets the requirement or not, and if not, constructing the point cloud refining unit again until the requirement is met; generating a training set to train the point cloud completion model; and finally, complementing the incomplete point cloud by using the trained model. According to the point cloud completion method provided by the invention, the incomplete input point cloud and the general point cloud are fully utilized to complement the object shape prior information provided by the output point cloud of the network, and the prior information is integrated and processed through the</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN113052955A
source esp@cenet
subjects CALCULATING
COMPUTING
COUNTING
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
title Point cloud completion method, system and application
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-13T02%3A51%3A53IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=LI%20JIAOJIAO&rft.date=2021-06-29&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN113052955A%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true