Learned Gradient Descent Performance in Bicubic Super-Resolution Task

Iaroslav Koshelev, Andrey Somov

    Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

    Abstract

    In most cases, being an ill-posed problem, image restoration opts to restore a high-quality image from a low-quality one, assuming that some degradation model produced given low-quality input. A lot of restoration methods were proposed for the case when linear degradation operator and i.i.d. Gaussian likelihood is assumed. However, such methods are known not to generalize well. They show a sub-par performance on real data, for which the actual degradation model is neither linear nor even exactly known. The state-of-the-art machine learning allows for overcoming this issue and learn a restoration model to the real data. The main drawback of such approaches is overfitting since to learn an inverse mapping between the low-quality and high-quality samples, they rely entirely on data. They do not utilize limited but existing knowledge of how degradation was performed. In this paper, we study learned gradient descent based image restoration and synthesis. Both linear and non-linear known restoration problems are considered, and research on how a known degradation model may be incorporated in a learned gradient-based restoration procedure is provided. Our results demonstrate that explicit usage of the degradation model and its learned linear and non-linear approximations boost restoration quality compared to a baseline without this feature.

    Original languageEnglish
    Title of host publicationIECON 2021 - 47th Annual Conference of the IEEE Industrial Electronics Society
    PublisherIEEE Computer Society
    ISBN (Electronic)9781665435543
    DOIs
    Publication statusPublished - 13 Oct 2021
    Event47th Annual Conference of the IEEE Industrial Electronics Society, IECON 2021 - Toronto, Canada
    Duration: 13 Oct 202116 Oct 2021

    Publication series

    NameIECON Proceedings (Industrial Electronics Conference)
    Volume2021-October

    Conference

    Conference47th Annual Conference of the IEEE Industrial Electronics Society, IECON 2021
    Country/TerritoryCanada
    CityToronto
    Period13/10/2116/10/21

    Keywords

    • image processing
    • inverse problems
    • machine learning
    • Super-resolution

    Fingerprint

    Dive into the research topics of 'Learned Gradient Descent Performance in Bicubic Super-Resolution Task'. Together they form a unique fingerprint.

    Cite this