Predicate |
Object |
assignee |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_ca46be4e68fa1f5a8b2ef4ab654c490a |
classificationCPCAdditional |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-10048 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20084 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20081 |
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/G06T7-41 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T3-4053 |
classificationIPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T3-40 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-41 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08 |
filingDate |
2022-03-21-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_f280abc1701b25bbd0242b1b99007d87 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_31873edf2e0d49a27e1eb7e2e4bb543c http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_73ec48ce7d0209fda15a3bcbed394707 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_3496124a29078db96fa05ce0a84a8771 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_6de332390016090697ad1ad36f26b02f http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_ed9664766f6d294a7f4ae2e5b0d517a0 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_275e916227f89425e005311b97087377 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_d865ecfe83cb6c00b6f56aabfa6afaa3 |
publicationDate |
2022-07-15-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber |
CN-114757825-A |
titleOfInvention |
Infrared image super-resolution reconstruction method and device based on feature separation |
abstract |
The invention discloses an infrared image super-resolution reconstruction method based on feature separation, comprising: acquiring an image to be processed; up-sampling the to-be-processed image to obtain a first image; Obtaining low-frequency features and low-frequency features of the first image; determining a structural image of the first image according to the low-frequency features, and obtaining texture information and a noise image of the first image according to the low-frequency features; Structural image and texture information, super-resolution reconstruction to obtain a second image. The feature separation network in the present invention can realize the high and low frequency separation of the low-resolution image and the high-resolution image, so that the high-frequency features can be better learned, and different networks are used for processing according to the characteristics of the separated structure image, and the full use of The input multi-scale features further guide the restoration of image details and improve the information content of the image. |
isCitedBy |
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-115358954-A |
priorityDate |
2022-03-21-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type |
http://data.epo.org/linked-data/def/patent/Publication |