Deep learning approach to video frame rate up-conversion using bilateral motion estimation

Junheum Park, Chul Lee, Chang Su Kim

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    3 Citations (Scopus)

    Abstract

    We propose a deep learning-based frame rate upconversion algorithm using bilateral motion estimation. We first estimate bilateral motion fields by employing a convolutional neural network. Also, we approximate intermediate bi-directional motion fields, assuming linear motions between successive frames. Finally, we develop the synthesis network to produce an intermediate frame by merging the warped frames, which are obtained using the two kinds of motion fields. Experimental results demonstrate that the proposed algorithm generates high-quality intermediate frames on challenging sequences with large motions and occlusion, and outperforms state-of-the-art conventional algorithms.

    Original languageEnglish
    Title of host publication2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2019
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages1970-1975
    Number of pages6
    ISBN (Electronic)9781728132488
    DOIs
    Publication statusPublished - 2019 Nov
    Event2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2019 - Lanzhou, China
    Duration: 2019 Nov 182019 Nov 21

    Publication series

    Name2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2019

    Conference

    Conference2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2019
    Country/TerritoryChina
    CityLanzhou
    Period19/11/1819/11/21

    ASJC Scopus subject areas

    • Information Systems

    Fingerprint

    Dive into the research topics of 'Deep learning approach to video frame rate up-conversion using bilateral motion estimation'. Together they form a unique fingerprint.

    Cite this