Motion blur video restoration method, device and apparatus
The invention discloses a motion blur video restoration method, device and apparatus The method comprises the following steps that: jointly using a plurality of frames of blurred images in a motion blurred video as input of a convolutional neural network; and modeling object feature deformation of a...
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Patent |
| Sprache: | chi ; eng |
| Schlagworte: | |
| 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 | ZENG QINGHAO HE QINYU ZHAO DONGNING ZHANG YONG MA SHAOYONG LIANG CHANGYIN |
| description | The invention discloses a motion blur video restoration method, device and apparatus The method comprises the following steps that: jointly using a plurality of frames of blurred images in a motion blurred video as input of a convolutional neural network; and modeling object feature deformation of a multi-frame blurred image as the input of the convolutional neural network by adopting a three-dimensional deformation convolutional network mode, and restoring the motion blurred video according to the modeling of the object feature deformation of the multi-frame blurred image as the input of theconvolutional neural network. Through the above mode, the object feature deformation in the motion blurred video can be effectively modeled, and the motion blurred video restoration effect can be effectively improved.
本发明公开了一种运动模糊视频复原方法和装置以及设备。其中，所述方法包括：将运动模糊视频中的多帧模糊图像共同作为卷积神经网络的输入，和采用三维变形卷积网络方式，对该作为卷积神经网络的输入的多帧模糊图像的物体特征形变进行建模，以及根据该对该作为卷积神经网络的输入的多帧模糊图像的物体特征形变进行的建模，对该运动模糊视频进行复原。通过上述方式，能够实现有效对运动模糊视频中的物体特征形变进行建模，能够有效提升运动模糊视频 |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN110390651A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN110390651A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN110390651A3</originalsourceid><addsrcrecordid>eNrjZLDyzS_JzM9TSMopLVIoy0xJzVcoSi0uyS9KBAvnppZk5KfoKKSklmUmpyok5qUoJBYUJAJlS4t5GFjTEnOKU3mhNDeDoptriLOHbmpBfnxqcUFicmpeakm8s5-hoYGxpYGZqaGjMTFqAID2LxI</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Motion blur video restoration method, device and apparatus</title><source>esp@cenet</source><creator>ZENG QINGHAO ; HE QINYU ; ZHAO DONGNING ; ZHANG YONG ; MA SHAOYONG ; LIANG CHANGYIN</creator><creatorcontrib>ZENG QINGHAO ; HE QINYU ; ZHAO DONGNING ; ZHANG YONG ; MA SHAOYONG ; LIANG CHANGYIN</creatorcontrib><description>The invention discloses a motion blur video restoration method, device and apparatus The method comprises the following steps that: jointly using a plurality of frames of blurred images in a motion blurred video as input of a convolutional neural network; and modeling object feature deformation of a multi-frame blurred image as the input of the convolutional neural network by adopting a three-dimensional deformation convolutional network mode, and restoring the motion blurred video according to the modeling of the object feature deformation of the multi-frame blurred image as the input of theconvolutional neural network. Through the above mode, the object feature deformation in the motion blurred video can be effectively modeled, and the motion blurred video restoration effect can be effectively improved.
本发明公开了一种运动模糊视频复原方法和装置以及设备。其中，所述方法包括：将运动模糊视频中的多帧模糊图像共同作为卷积神经网络的输入，和采用三维变形卷积网络方式，对该作为卷积神经网络的输入的多帧模糊图像的物体特征形变进行建模，以及根据该对该作为卷积神经网络的输入的多帧模糊图像的物体特征形变进行的建模，对该运动模糊视频进行复原。通过上述方式，能够实现有效对运动模糊视频中的物体特征形变进行建模，能够有效提升运动模糊视频</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTING ; COUNTING ; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ; PHYSICS</subject><creationdate>2019</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&date=20191029&DB=EPODOC&CC=CN&NR=110390651A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76289</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20191029&DB=EPODOC&CC=CN&NR=110390651A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>ZENG QINGHAO</creatorcontrib><creatorcontrib>HE QINYU</creatorcontrib><creatorcontrib>ZHAO DONGNING</creatorcontrib><creatorcontrib>ZHANG YONG</creatorcontrib><creatorcontrib>MA SHAOYONG</creatorcontrib><creatorcontrib>LIANG CHANGYIN</creatorcontrib><title>Motion blur video restoration method, device and apparatus</title><description>The invention discloses a motion blur video restoration method, device and apparatus The method comprises the following steps that: jointly using a plurality of frames of blurred images in a motion blurred video as input of a convolutional neural network; and modeling object feature deformation of a multi-frame blurred image as the input of the convolutional neural network by adopting a three-dimensional deformation convolutional network mode, and restoring the motion blurred video according to the modeling of the object feature deformation of the multi-frame blurred image as the input of theconvolutional neural network. Through the above mode, the object feature deformation in the motion blurred video can be effectively modeled, and the motion blurred video restoration effect can be effectively improved.
本发明公开了一种运动模糊视频复原方法和装置以及设备。其中，所述方法包括：将运动模糊视频中的多帧模糊图像共同作为卷积神经网络的输入，和采用三维变形卷积网络方式，对该作为卷积神经网络的输入的多帧模糊图像的物体特征形变进行建模，以及根据该对该作为卷积神经网络的输入的多帧模糊图像的物体特征形变进行的建模，对该运动模糊视频进行复原。通过上述方式，能够实现有效对运动模糊视频中的物体特征形变进行建模，能够有效提升运动模糊视频</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>2019</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZLDyzS_JzM9TSMopLVIoy0xJzVcoSi0uyS9KBAvnppZk5KfoKKSklmUmpyok5qUoJBYUJAJlS4t5GFjTEnOKU3mhNDeDoptriLOHbmpBfnxqcUFicmpeakm8s5-hoYGxpYGZqaGjMTFqAID2LxI</recordid><startdate>20191029</startdate><enddate>20191029</enddate><creator>ZENG QINGHAO</creator><creator>HE QINYU</creator><creator>ZHAO DONGNING</creator><creator>ZHANG YONG</creator><creator>MA SHAOYONG</creator><creator>LIANG CHANGYIN</creator><scope>EVB</scope></search><sort><creationdate>20191029</creationdate><title>Motion blur video restoration method, device and apparatus</title><author>ZENG QINGHAO ; HE QINYU ; ZHAO DONGNING ; ZHANG YONG ; MA SHAOYONG ; LIANG CHANGYIN</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN110390651A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2019</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>ZENG QINGHAO</creatorcontrib><creatorcontrib>HE QINYU</creatorcontrib><creatorcontrib>ZHAO DONGNING</creatorcontrib><creatorcontrib>ZHANG YONG</creatorcontrib><creatorcontrib>MA SHAOYONG</creatorcontrib><creatorcontrib>LIANG CHANGYIN</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>ZENG QINGHAO</au><au>HE QINYU</au><au>ZHAO DONGNING</au><au>ZHANG YONG</au><au>MA SHAOYONG</au><au>LIANG CHANGYIN</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Motion blur video restoration method, device and apparatus</title><date>2019-10-29</date><risdate>2019</risdate><abstract>The invention discloses a motion blur video restoration method, device and apparatus The method comprises the following steps that: jointly using a plurality of frames of blurred images in a motion blurred video as input of a convolutional neural network; and modeling object feature deformation of a multi-frame blurred image as the input of the convolutional neural network by adopting a three-dimensional deformation convolutional network mode, and restoring the motion blurred video according to the modeling of the object feature deformation of the multi-frame blurred image as the input of theconvolutional neural network. Through the above mode, the object feature deformation in the motion blurred video can be effectively modeled, and the motion blurred video restoration effect can be effectively improved.
本发明公开了一种运动模糊视频复原方法和装置以及设备。其中，所述方法包括：将运动模糊视频中的多帧模糊图像共同作为卷积神经网络的输入，和采用三维变形卷积网络方式，对该作为卷积神经网络的输入的多帧模糊图像的物体特征形变进行建模，以及根据该对该作为卷积神经网络的输入的多帧模糊图像的物体特征形变进行的建模，对该运动模糊视频进行复原。通过上述方式，能够实现有效对运动模糊视频中的物体特征形变进行建模，能够有效提升运动模糊视频</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN110390651A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTING COUNTING IMAGE DATA PROCESSING OR GENERATION, IN GENERAL PHYSICS |
| title | Motion blur video restoration method, device and apparatus |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-04T19%3A11%3A25IST&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=ZENG%20QINGHAO&rft.date=2019-10-29&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN110390651A%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 |