Learned Gradient Descent Performance in Bicubic Super-Resolution Task

Iaroslav Koshelev, Andrey Somov

    Результат исследований: Глава в книге, отчете, сборнике статейМатериалы для конференциирецензирование

    Аннотация

    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.

    Язык оригиналаАнглийский
    Название основной публикацииIECON 2021 - 47th Annual Conference of the IEEE Industrial Electronics Society
    ИздательIEEE Computer Society
    ISBN (электронное издание)9781665435543
    DOI
    СостояниеОпубликовано - 13 окт. 2021
    Событие47th Annual Conference of the IEEE Industrial Electronics Society, IECON 2021 - Toronto, Канада
    Продолжительность: 13 окт. 202116 окт. 2021

    Серия публикаций

    НазваниеIECON Proceedings (Industrial Electronics Conference)
    Том2021-October

    Конференция

    Конференция47th Annual Conference of the IEEE Industrial Electronics Society, IECON 2021
    Страна/TерриторияКанада
    ГородToronto
    Период13/10/2116/10/21

    Fingerprint

    Подробные сведения о темах исследования «Learned Gradient Descent Performance in Bicubic Super-Resolution Task». Вместе они формируют уникальный семантический отпечаток (fingerprint).

    Цитировать