Due to weather, camera technology, compression transmission, etc., people are not always able to obtain highresolution images that meet the needs of specific scenes. A deep recursive multi-scale residual network (DRMRN) for single image super-resolution is possessed to solve this problem. The proposed multi-scale residual block is based on the basic residual unit and different branches consist of convolution kernels of different sizes. Adaptive image feature extraction is beneficial to fully extract and utilize LR image features. In addition, our network has both local residual learning and global residual learning, which reduces the difficulty of training and solves the problem of gradient disappearance and gradient explosion in the training process. Compared with other models, the proposed model improves the reconstruction effect, and the reconstruction results have higher PSNR and SSIM values.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Deep recursive multi-scale residual network for single image super-resolution reconstruction


    Beteiligte:
    Zhang, Cheng (Autor:in) / He, Xuemei (Autor:in) / Wang, Haimin (Autor:in) / Wang, Cheng (Autor:in) / Li, Zhiyong (Autor:in) / Zhang, Kun (Autor:in)


    Erscheinungsdatum :

    2021-10-20


    Format / Umfang :

    1997255 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    RDRN: Recursively Defined Residual Network for Image Super-Resolution

    Panaetov, Alexander / Daou, Karim Elhadji / Samenko, Igor et al. | British Library Conference Proceedings | 2023


    Image acquisition modeling for super-resolution reconstruction

    Gevrekci, M. / Gunturk, B.K. | IEEE | 2005


    Image Acquisition Modeling for Super-Resolution Reconstruction

    Gevrekci, M. / Gunturk, B. K. | British Library Conference Proceedings | 2005


    Multi-Scale, Super-Resolution Remote Imaging via Deep Conditional Normalizing Flows

    Heintz, Aneesh / Peck, Mason A. / Mackey, Ian | AIAA | 2022


    MULTIPLE-IMAGE SUPER-RESOLUTION RECONSTRUCTION USING DEEP LEARNING: A SENTINEL-2 CASE STUDY

    Kawulok, Michal / Tarasiewicz, Tomasz / Ziaja, Maciej et al. | TIBKAT | 2022