Point cloud registration method for linear spatial diffusion

Point cloud registration method for linear spatial diffusion

The invention discloses a point cloud registration method for linear spatial diffusion. The method comprises the following steps: acquiring a source point cloud and a target point cloud to be registered; performing global feature extraction on the source point cloud and the target point cloud to obt...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: MIAO QIGUANG, WU YUE, YUAN YONGZHE, GAO ZHIGANG, LI HAO, GONG MAOGUO, ZHANG MINGYANG, MA WENPING
Format: Patent
Sprache:chi ; eng
Schlagworte:
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
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 MIAO QIGUANG
WU YUE
YUAN YONGZHE
GAO ZHIGANG
LI HAO
GONG MAOGUO
ZHANG MINGYANG
MA WENPING
description The invention discloses a point cloud registration method for linear spatial diffusion. The method comprises the following steps: acquiring a source point cloud and a target point cloud to be registered; performing global feature extraction on the source point cloud and the target point cloud to obtain a source point cloud global feature and a target point cloud global feature; reasoning prior rigid transformation by using a diffusion model; the diffusion model is obtained by training based on a plurality of noise rigid transformations and corresponding real rigid transformations, the real rigid transformations are rigid transformations between registered sample source point clouds and sample target point clouds, and the noise rigid transformations are rigid transformations correspondingly obtained by performing forward diffusion noise addition on the real rigid transformations; and predicting a point cloud registration result of the source point cloud and the target point cloud according to the source point
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN118570266A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN118570266A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN118570266A3</originalsourceid><addsrcrecordid>eNrjZLAJyM_MK1FIzskvTVEoSk3PLC4pSizJzM9TyE0tychPUUjLL1LIycxLTSxSKC4AyiTmKKRkpqWVFgPV8DCwpiXmFKfyQmluBkU31xBnD93Ugvz4VKDy5NS81JJ4Zz9DQwtTcwMjMzNHY2LUAAAYYzA_</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Point cloud registration method for linear spatial diffusion</title><source>esp@cenet</source><creator>MIAO QIGUANG ; WU YUE ; YUAN YONGZHE ; GAO ZHIGANG ; LI HAO ; GONG MAOGUO ; ZHANG MINGYANG ; MA WENPING</creator><creatorcontrib>MIAO QIGUANG ; WU YUE ; YUAN YONGZHE ; GAO ZHIGANG ; LI HAO ; GONG MAOGUO ; ZHANG MINGYANG ; MA WENPING</creatorcontrib><description>The invention discloses a point cloud registration method for linear spatial diffusion. The method comprises the following steps: acquiring a source point cloud and a target point cloud to be registered; performing global feature extraction on the source point cloud and the target point cloud to obtain a source point cloud global feature and a target point cloud global feature; reasoning prior rigid transformation by using a diffusion model; the diffusion model is obtained by training based on a plurality of noise rigid transformations and corresponding real rigid transformations, the real rigid transformations are rigid transformations between registered sample source point clouds and sample target point clouds, and the noise rigid transformations are rigid transformations correspondingly obtained by performing forward diffusion noise addition on the real rigid transformations; and predicting a point cloud registration result of the source point cloud and the target point cloud according to the source point</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ; PHYSICS</subject><creationdate>2024</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=20240830&amp;DB=EPODOC&amp;CC=CN&amp;NR=118570266A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,777,882,25545,76296</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20240830&amp;DB=EPODOC&amp;CC=CN&amp;NR=118570266A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>MIAO QIGUANG</creatorcontrib><creatorcontrib>WU YUE</creatorcontrib><creatorcontrib>YUAN YONGZHE</creatorcontrib><creatorcontrib>GAO ZHIGANG</creatorcontrib><creatorcontrib>LI HAO</creatorcontrib><creatorcontrib>GONG MAOGUO</creatorcontrib><creatorcontrib>ZHANG MINGYANG</creatorcontrib><creatorcontrib>MA WENPING</creatorcontrib><title>Point cloud registration method for linear spatial diffusion</title><description>The invention discloses a point cloud registration method for linear spatial diffusion. The method comprises the following steps: acquiring a source point cloud and a target point cloud to be registered; performing global feature extraction on the source point cloud and the target point cloud to obtain a source point cloud global feature and a target point cloud global feature; reasoning prior rigid transformation by using a diffusion model; the diffusion model is obtained by training based on a plurality of noise rigid transformations and corresponding real rigid transformations, the real rigid transformations are rigid transformations between registered sample source point clouds and sample target point clouds, and the noise rigid transformations are rigid transformations correspondingly obtained by performing forward diffusion noise addition on the real rigid transformations; and predicting a point cloud registration result of the source point cloud and the target point cloud according to the source point</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</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>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZLAJyM_MK1FIzskvTVEoSk3PLC4pSizJzM9TyE0tychPUUjLL1LIycxLTSxSKC4AyiTmKKRkpqWVFgPV8DCwpiXmFKfyQmluBkU31xBnD93Ugvz4VKDy5NS81JJ4Zz9DQwtTcwMjMzNHY2LUAAAYYzA_</recordid><startdate>20240830</startdate><enddate>20240830</enddate><creator>MIAO QIGUANG</creator><creator>WU YUE</creator><creator>YUAN YONGZHE</creator><creator>GAO ZHIGANG</creator><creator>LI HAO</creator><creator>GONG MAOGUO</creator><creator>ZHANG MINGYANG</creator><creator>MA WENPING</creator><scope>EVB</scope></search><sort><creationdate>20240830</creationdate><title>Point cloud registration method for linear spatial diffusion</title><author>MIAO QIGUANG ; WU YUE ; YUAN YONGZHE ; GAO ZHIGANG ; LI HAO ; GONG MAOGUO ; ZHANG MINGYANG ; MA WENPING</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN118570266A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2024</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>MIAO QIGUANG</creatorcontrib><creatorcontrib>WU YUE</creatorcontrib><creatorcontrib>YUAN YONGZHE</creatorcontrib><creatorcontrib>GAO ZHIGANG</creatorcontrib><creatorcontrib>LI HAO</creatorcontrib><creatorcontrib>GONG MAOGUO</creatorcontrib><creatorcontrib>ZHANG MINGYANG</creatorcontrib><creatorcontrib>MA WENPING</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>MIAO QIGUANG</au><au>WU YUE</au><au>YUAN YONGZHE</au><au>GAO ZHIGANG</au><au>LI HAO</au><au>GONG MAOGUO</au><au>ZHANG MINGYANG</au><au>MA WENPING</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Point cloud registration method for linear spatial diffusion</title><date>2024-08-30</date><risdate>2024</risdate><abstract>The invention discloses a point cloud registration method for linear spatial diffusion. The method comprises the following steps: acquiring a source point cloud and a target point cloud to be registered; performing global feature extraction on the source point cloud and the target point cloud to obtain a source point cloud global feature and a target point cloud global feature; reasoning prior rigid transformation by using a diffusion model; the diffusion model is obtained by training based on a plurality of noise rigid transformations and corresponding real rigid transformations, the real rigid transformations are rigid transformations between registered sample source point clouds and sample target point clouds, and the noise rigid transformations are rigid transformations correspondingly obtained by performing forward diffusion noise addition on the real rigid transformations; and predicting a point cloud registration result of the source point cloud and the target point cloud according to the source point</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN118570266A
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
title Point cloud registration method for linear spatial diffusion
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-18T21%3A52%3A57IST&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=MIAO%20QIGUANG&rft.date=2024-08-30&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN118570266A%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