In this paper, we propose a learning method for deblurring Gaussian blurred images blindly by exploiting edge cues via deep multi-scales generative adversarial network: DeepEdgeGAN. We proposed the edges of the blurred images to be incorporated with the blurred image as the input of the DeepEdgeGAN to provide a strong prior constraint for the restoration, which is beneficial to solve the problem that gradients of the restored images with GANs methods tend to be smooth and not clear enough. Further, we introduce the perceptual and edge as well as scale losses to train the DeepEdgeGAN. With the trained end-to-end model, we directly restore the latent sharp images from blurred images and avoiding the estimation of pixel-kernel. Qualitative and quantitative experiments demonstrate that the visual effect of the restored images significantly improves better.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Blind deblurring of Gaussian blurred images by blurred edge image


    Contributors:
    Li, Yacheng (author) / Li, Lerenhan (author) / Li, Wenhao (author) / Fan, Zhihua (author) / Chen, Zongmei (author) / Gao, Changxin (author) / Sang, Nong (author)

    Conference:

    MIPPR 2019: Pattern Recognition and Computer Vision ; 2019 ; Wuhan,China


    Published in:

    Proc. SPIE ; 11430


    Publication date :

    2020-02-14





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Blind deblurring of Gaussian blurred images by blurred edge image

    Li, Yacheng / Li, Lerenhan / Li, Wenhao et al. | British Library Conference Proceedings | 2020


    Image processing of blurred medical images

    Doherty, A. / Payne, R. R. / IEE; Science, Education and Technology Division | British Library Conference Proceedings | 1993


    INTERMODAL - Blurred image

    Online Contents | 1998


    Parametric Modeling of Blurred Images for Image Restoration

    Premaratne, P. / Ko, C. C. | British Library Conference Proceedings | 2000


    High-accuracy edge detection with Blurred Edge Model

    Ye, J. / Fu, G. / Poudel, U. P. | British Library Online Contents | 2005