VIDEO COMPRESSION BASED ON LONG RANGE END-TO-END DEEP LEARNING

At least a method and an apparatus are presented for efficiently encoding or decoding video. For example, a plurality of frames is provided to a motion estimator to produce an output comprising estimated motion information. The estimated motion information is provided to an auto-encoder or an auto-d...

Full description

Saved in:
Bibliographic Details
Main Authors Galpin, Franck, Begaint, Jean, Pham, Xuan Hien
Format Patent
LanguageEnglish
Published 24.11.2022
Subjects
ELECTRIC COMMUNICATION TECHNIQUE
ELECTRICITY
PICTORIAL COMMUNICATION, e.g. TELEVISION
Online AccessGet full text

Cover

More Information
Summary:At least a method and an apparatus are presented for efficiently encoding or decoding video. For example, a plurality of frames is provided to a motion estimator to produce an output comprising estimated motion information. The estimated motion information is provided to an auto-encoder or an auto-decoder to produce an output comprising reconstructed motion field. The reconstructed motion field and one or more decoded frames of the plurality of frames are provided to a deep neural network to produce an output comprising refined bi-directional motion field. The video is encoded or decoded based on the refined bi-directional motion field.
Bibliography:Application Number: US202017761487