| Predicate |
Object |
| assignee |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_fc9fc0a1a0fa2305cd0c4ace997bf0c2 |
| classificationCPCAdditional |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20132
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/G06N3-08
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T5-003
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T3-4053
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T5-50 |
| classificationIPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T3-40
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T5-50
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/G06T5-00 |
| filingDate |
2022-03-03-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| inventor |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_f6815b497ac45dcd6b7d9cdacfab4ad6
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_972118dc61b126e47959f5269a046151
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_7e247d26d0eec0b56f602f335eb2680b
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_0ca6e61b83db7dcd851628c5c648b2b1
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_5a8f98707af439fbf5daa750f52593ef
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_2329180f8ee1b73d406d63ea3985dca1 |
| publicationDate |
2022-06-03-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber |
CN-114581304-A |
| titleOfInvention |
A method and system for image super-resolution and dehazing fusion based on recurrent network |
| abstract |
The invention discloses an image super-resolution and dehazing fusion method and system based on a cyclic network. The method steps are: acquiring a low-resolution foggy image and a high-resolution fog-free image without pairing; constructing an unsupervised cyclic network system; train the recurrent network system; in the first branch of the recurrent network, the low-resolution hazy image L is input to the first generation network G L2H to obtain an estimated high-resolution dehazed image image It is then input to the second generation network G H2L to obtain a reconstructed low-resolution hazy image ~L; in the second branch of the recurrent network, the high-resolution haze-free image H undergoes a similar inverse process of estimation and reconstruction. The system includes an image sample acquisition module, a recurrent network system building module and a recurrent network system training module. The network of the present invention adopts an unsupervised learning method without pairing data, and adds super-resolution reconstruction while dehazing the degraded foggy image. module, which enhances the details of the image and makes the restored image clearer. |
| isCitedBy |
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-115578263-B
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-115578263-A |
| priorityDate |
2022-03-03-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| type |
http://data.epo.org/linked-data/def/patent/Publication |