http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-111540000-B
Outgoing Links
| Predicate | Object |
|---|---|
| classificationCPCAdditional | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-30244 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-20081 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T2207-10004 |
| classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-207 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N20-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-73 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-50 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06T7-20 |
| classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-73 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-50 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06T7-207 |
| filingDate | 2020-04-28-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| grantDate | 2021-11-05-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationDate | 2021-11-05-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber | CN-111540000-B |
| titleOfInvention | Scene depth and camera motion prediction method and apparatus, electronic device and medium |
| abstract | The present disclosure relates to a scene depth and camera motion prediction method and device, electronic device and medium, the method includes: acquiring a target image frame at time t; The target image frame is subjected to scene depth prediction, and a predicted depth map corresponding to the target image frame is determined, wherein the first hidden state information includes feature information related to the scene depth, and the scene depth prediction network is based on camera motion. Predictive network-assisted training. In the embodiment of the present disclosure, a predicted depth map with higher prediction accuracy corresponding to the target image frame can be obtained. |
| priorityDate | 2020-04-28-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Total number of triples: 23.