http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114494576-A
Outgoing Links
Predicate | Object |
---|---|
assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_ac31afbea1cbbb03498644721ffb4a62 |
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T17-00 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T17-00 |
filingDate | 2021-12-23-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_82c28c9b37eb985bee5535affeb13d6c http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_6f328e2f070ea3881e8293cfa434e1ab http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_ba97e020c79aa18094c5962a254bb875 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_acc7a9f031348071b01d05bb689b6169 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_c3b0a2d14bff8c938f8a1714746e677d |
publicationDate | 2022-05-13-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | CN-114494576-A |
titleOfInvention | A fast and high-precision multi-view face 3D reconstruction method based on implicit function |
abstract | The invention discloses a fast and high-precision multi-viewpoint face three-dimensional reconstruction method based on an implicit function, which belongs to the field of computer vision. The method includes: acquiring multi-view face data; using a face parameterized model to generate an initial face template, and expanding the face template into a plane to construct a solution space; using an implicit function to represent the face surface, and constructing a face based on the implicit function Surface prediction network; construct solution space regularization network; generate texture of predicted face model according to multi-view images; construct displacement map prediction network; train network to predict high-precision 3D face model through input multi-view images. The three-dimensional face model reconstructed by the method of the invention has high precision, retains the detailed information of facial pores, and has the advantage of fast reconstruction speed. |
priorityDate | 2021-12-23-04:00^^<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/compound/CID21787 http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID447650467 |
Total number of triples: 21.