http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-115170916-A

Outgoing Links

Predicate Object
assignee http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_44e8ff80202d6fd5bc7e7aebc44390f1
classificationCPCAdditional http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20221
classificationCPCInventive http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V10-806
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06V10-82
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T5-50
classificationIPCInventive http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T5-50
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V10-82
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06V10-80
filingDate 2022-09-06-04:00^^<http://www.w3.org/2001/XMLSchema#date>
inventor http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_fefe83e4df243dc8c768193d02628f73
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_d412f6ad39e358f444449cd30165c910
publicationDate 2022-10-11-04:00^^<http://www.w3.org/2001/XMLSchema#date>
publicationNumber CN-115170916-A
titleOfInvention An image reconstruction method and system for multi-scale feature fusion
abstract The invention discloses a multi-scale feature fusion image reconstruction method and system in the field of image reconstruction, including: compressing and measuring an original image to obtain a measurement vector; generating an initial reconstructed image according to the measurement vector; The image is extracted in turn to obtain a residual feature set; the residual feature En is input to the dense module of various scale convolution kernels to extract the dense feature T 1 ; the dense feature T 1 and the residual feature E n- are extracted by the attention module 1. Perform local feature fusion to form a dense feature T 2 ; repeat the iteration until the global residual feature fusion is completed, and obtain a global fusion feature; after calculating the residual of the global fusion feature, add it to the initial reconstructed image to obtain a final reconstructed image; Image reconstruction quality and reduce the computational load of the network.
priorityDate 2022-09-06-04:00^^<http://www.w3.org/2001/XMLSchema#date>
type http://data.epo.org/linked-data/def/patent/Publication

Incoming Links

Predicate Subject
isCitedBy http://rdf.ncbi.nlm.nih.gov/pubchem/patent/US-2019147589-A1
isDiscussedBy http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID419559581
http://rdf.ncbi.nlm.nih.gov/pubchem/compound/CID297

Total number of triples: 20.