Invention Grant
- Patent Title: Training end-to-end video processes
-
Application No.: US15707294Application Date: 2017-09-18
-
Publication No.: US10666962B2Publication Date: 2020-05-26
- Inventor: Zehan Wang , Robert David Bishop , Ferenc Huszar , Lucas Theis
- Applicant: Magic Pony Technology Limited
- Applicant Address: GB London
- Assignee: Magic Pony Technology Limited
- Current Assignee: Magic Pony Technology Limited
- Current Assignee Address: GB London
- Agency: Brake Hughes Bellermann LLP
- Priority: com.zzzhc.datahub.patent.etl.us.BibliographicData$PriorityClaim@62d72aed com.zzzhc.datahub.patent.etl.us.BibliographicData$PriorityClaim@3d7d5a3f com.zzzhc.datahub.patent.etl.us.BibliographicData$PriorityClaim@2a4e6154 com.zzzhc.datahub.patent.etl.us.BibliographicData$PriorityClaim@29bfdcd9 com.zzzhc.datahub.patent.etl.us.BibliographicData$PriorityClaim@72640b41 com.zzzhc.datahub.patent.etl.us.BibliographicData$PriorityClaim@251f1b90 com.zzzhc.datahub.patent.etl.us.BibliographicData$PriorityClaim@7c829aa6 com.zzzhc.datahub.patent.etl.us.BibliographicData$PriorityClaim@2b8cc8fb com.zzzhc.datahub.patent.etl.us.BibliographicData$PriorityClaim@7960e0c8 com.zzzhc.datahub.patent.etl.us.BibliographicData$PriorityClaim@247eb7ef com.zzzhc.datahub.patent.etl.us.BibliographicData$PriorityClaim@4cc15e6c com.zzzhc.datahub.patent.etl.us.BibliographicData$PriorityClaim@1c78c1f com.zzzhc.datahub.patent.etl.us.BibliographicData$PriorityClaim@7fdf5a4f com.zzzhc.datahub.patent.etl.us.BibliographicData$PriorityClaim@2e4f4b94 com.zzzhc.datahub.patent.etl.us.BibliographicData$PriorityClaim@683b520f com.zzzhc.datahub.patent.etl.us.BibliographicData$PriorityClaim@55219c63 com.zzzhc.datahub.patent.etl.us.BibliographicData$PriorityClaim@5029b9aa com.zzzhc.datahub.patent.etl.us.BibliographicData$PriorityClaim@4ee4bd0 com.zzzhc.datahub.patent.etl.us.BibliographicData$PriorityClaim@3677da68
- Main IPC: H04N19/46
- IPC: H04N19/46 ; G06T9/00 ; H04N19/154 ; H04N19/85 ; H04N19/59 ; G06T3/40
Abstract:
Disclosed is method for training a plurality of visual processing algorithms for processing visual data. The method includes using a pre-processing hierarchical algorithm to process the visual data prior to encoding the visual data in visual data processing, and using a post-processing hierarchical algorithm to further process the visual data following decoding visual data in visual data processing. The encoding and decoding are performed with respect to a predetermined visual data codec and may be content specific.
Public/Granted literature
- US20180131953A1 TRAINING END-TO-END VIDEO PROCESSES Public/Granted day:2018-05-10
Information query
