Reconstruction method of head three-dimensional model and electronic equipment
The invention provides a reconstruction method of a three-dimensional head model and electronic equipment, which are used for improving the quality of the three-dimensional head model. Comprising the following steps: for any target object, inputting a multi-view RGBD image of the target object into...
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 | ZHAO XIAOCHEN LIANG DACAI WU LIANPENG WANG BAOYUN LIU YEBIN LIU SHUAI YU ZHITAO |
| description | The invention provides a reconstruction method of a three-dimensional head model and electronic equipment, which are used for improving the quality of the three-dimensional head model. Comprising the following steps: for any target object, inputting a multi-view RGBD image of the target object into a pre-trained head three-dimensional model reconstruction neural network to obtain a head three-dimensional model; wherein the training mode of the head three-dimensional model reconstruction neural network is as follows: inputting a training sample into the head three-dimensional model reconstruction neural network to obtain a predicted sdf value of each rendered image, each predicted rendered image and a head three-dimensional model, the training sample comprises each rendered image after the head three-dimensional model is rendered at different visual angles and illumination and a target sdf value of each rendered image; determining a target loss value by using a first intermediate loss value obtained based on e |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN115272565A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN115272565A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN115272565A3</originalsourceid><addsrcrecordid>eNqNyrEOwiAURmEWB6O-w_UBOrQGnZtG49TBuDcE_qYkwEW4fX87-ABOZzjfXo0vWE5VymrFc6IIWdgRz7TAOJKlAI3zEalu2wSK7BDIJEcIsFI4eUv4rD5vRo5qN5tQcfr1oM6P-3t4Nsg8oWZjkSDTMLat7m6dvur-8o_5Al__Nx8</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Reconstruction method of head three-dimensional model and electronic equipment</title><source>esp@cenet</source><creator>ZHAO XIAOCHEN ; LIANG DACAI ; WU LIANPENG ; WANG BAOYUN ; LIU YEBIN ; LIU SHUAI ; YU ZHITAO</creator><creatorcontrib>ZHAO XIAOCHEN ; LIANG DACAI ; WU LIANPENG ; WANG BAOYUN ; LIU YEBIN ; LIU SHUAI ; YU ZHITAO</creatorcontrib><description>The invention provides a reconstruction method of a three-dimensional head model and electronic equipment, which are used for improving the quality of the three-dimensional head model. Comprising the following steps: for any target object, inputting a multi-view RGBD image of the target object into a pre-trained head three-dimensional model reconstruction neural network to obtain a head three-dimensional model; wherein the training mode of the head three-dimensional model reconstruction neural network is as follows: inputting a training sample into the head three-dimensional model reconstruction neural network to obtain a predicted sdf value of each rendered image, each predicted rendered image and a head three-dimensional model, the training sample comprises each rendered image after the head three-dimensional model is rendered at different visual angles and illumination and a target sdf value of each rendered image; determining a target loss value by using a first intermediate loss value obtained based on e</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>2022</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=20221101&DB=EPODOC&CC=CN&NR=115272565A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76289</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20221101&DB=EPODOC&CC=CN&NR=115272565A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>ZHAO XIAOCHEN</creatorcontrib><creatorcontrib>LIANG DACAI</creatorcontrib><creatorcontrib>WU LIANPENG</creatorcontrib><creatorcontrib>WANG BAOYUN</creatorcontrib><creatorcontrib>LIU YEBIN</creatorcontrib><creatorcontrib>LIU SHUAI</creatorcontrib><creatorcontrib>YU ZHITAO</creatorcontrib><title>Reconstruction method of head three-dimensional model and electronic equipment</title><description>The invention provides a reconstruction method of a three-dimensional head model and electronic equipment, which are used for improving the quality of the three-dimensional head model. Comprising the following steps: for any target object, inputting a multi-view RGBD image of the target object into a pre-trained head three-dimensional model reconstruction neural network to obtain a head three-dimensional model; wherein the training mode of the head three-dimensional model reconstruction neural network is as follows: inputting a training sample into the head three-dimensional model reconstruction neural network to obtain a predicted sdf value of each rendered image, each predicted rendered image and a head three-dimensional model, the training sample comprises each rendered image after the head three-dimensional model is rendered at different visual angles and illumination and a target sdf value of each rendered image; determining a target loss value by using a first intermediate loss value obtained based on e</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>2022</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNyrEOwiAURmEWB6O-w_UBOrQGnZtG49TBuDcE_qYkwEW4fX87-ABOZzjfXo0vWE5VymrFc6IIWdgRz7TAOJKlAI3zEalu2wSK7BDIJEcIsFI4eUv4rD5vRo5qN5tQcfr1oM6P-3t4Nsg8oWZjkSDTMLat7m6dvur-8o_5Al__Nx8</recordid><startdate>20221101</startdate><enddate>20221101</enddate><creator>ZHAO XIAOCHEN</creator><creator>LIANG DACAI</creator><creator>WU LIANPENG</creator><creator>WANG BAOYUN</creator><creator>LIU YEBIN</creator><creator>LIU SHUAI</creator><creator>YU ZHITAO</creator><scope>EVB</scope></search><sort><creationdate>20221101</creationdate><title>Reconstruction method of head three-dimensional model and electronic equipment</title><author>ZHAO XIAOCHEN ; LIANG DACAI ; WU LIANPENG ; WANG BAOYUN ; LIU YEBIN ; LIU SHUAI ; YU ZHITAO</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN115272565A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2022</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>ZHAO XIAOCHEN</creatorcontrib><creatorcontrib>LIANG DACAI</creatorcontrib><creatorcontrib>WU LIANPENG</creatorcontrib><creatorcontrib>WANG BAOYUN</creatorcontrib><creatorcontrib>LIU YEBIN</creatorcontrib><creatorcontrib>LIU SHUAI</creatorcontrib><creatorcontrib>YU ZHITAO</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>ZHAO XIAOCHEN</au><au>LIANG DACAI</au><au>WU LIANPENG</au><au>WANG BAOYUN</au><au>LIU YEBIN</au><au>LIU SHUAI</au><au>YU ZHITAO</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Reconstruction method of head three-dimensional model and electronic equipment</title><date>2022-11-01</date><risdate>2022</risdate><abstract>The invention provides a reconstruction method of a three-dimensional head model and electronic equipment, which are used for improving the quality of the three-dimensional head model. Comprising the following steps: for any target object, inputting a multi-view RGBD image of the target object into a pre-trained head three-dimensional model reconstruction neural network to obtain a head three-dimensional model; wherein the training mode of the head three-dimensional model reconstruction neural network is as follows: inputting a training sample into the head three-dimensional model reconstruction neural network to obtain a predicted sdf value of each rendered image, each predicted rendered image and a head three-dimensional model, the training sample comprises each rendered image after the head three-dimensional model is rendered at different visual angles and illumination and a target sdf value of each rendered image; determining a target loss value by using a first intermediate loss value obtained based on e</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN115272565A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING IMAGE DATA PROCESSING OR GENERATION, IN GENERAL PHYSICS |
| title | Reconstruction method of head three-dimensional model and electronic equipment |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-08T19%3A32%3A07IST&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=ZHAO%20XIAOCHEN&rft.date=2022-11-01&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN115272565A%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 |