http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114742972-A

Outgoing Links

Predicate Object
assignee http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_31113ee5391df01cbc1c441c2f3735e2
classificationCPCAdditional http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20084
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20081
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-10024
classificationCPCInventive http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-04
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T17-20
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T15-005
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-084
classificationIPCInventive http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T15-00
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T17-20
filingDate 2022-04-08-04:00^^<http://www.w3.org/2001/XMLSchema#date>
inventor http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_2bf03979553b6dd35fceb66216237cc1
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_3e2247f362141feffa74df96474abfb3
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_6a2f2c5bcce74928e74eb02f8ae76de4
publicationDate 2022-07-12-04:00^^<http://www.w3.org/2001/XMLSchema#date>
publicationNumber CN-114742972-A
titleOfInvention 3D face reconstruction method and device based on face RGB image
abstract The present application provides a three-dimensional face reconstruction method and device based on a face RGB image, the geometric coefficients and color coefficients of the three-dimensional deformation model are regressed through the first-level residual network; the three-dimensional face shape is reconstructed based on these coefficients, and the three-dimensional The face shape is projected and rendered to obtain a two-dimensional face image; the two-dimensional face image and the original RGB are provided as input to the second residual network to regress the residuals of geometric coefficients and color coefficients, and the first-level residual network is obtained. The coefficients of , and the residuals of the coefficients obtained by the second residual network are added to obtain the final three-dimensional deformation model coefficients. Through this two-stage residual network structure, more accurate coefficient regression is achieved, and the accuracy of face reconstruction is improved.
priorityDate 2022-04-08-04:00^^<http://www.w3.org/2001/XMLSchema#date>
type http://data.epo.org/linked-data/def/patent/Publication

Incoming Links

Predicate Subject
isDiscussedBy http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID419701332
http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID413130148
http://rdf.ncbi.nlm.nih.gov/pubchem/compound/CID16734986
http://rdf.ncbi.nlm.nih.gov/pubchem/compound/CID22978774

Total number of triples: 26.