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.
Blind deblurring of Gaussian blurred images by blurred edge image
MIPPR 2019: Pattern Recognition and Computer Vision ; 2019 ; Wuhan,China
Proc. SPIE ; 11430
2020-02-14
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Blind deblurring of Gaussian blurred images by blurred edge image
British Library Conference Proceedings | 2020
|Image processing of blurred medical images
British Library Conference Proceedings | 1993
|Online Contents | 1998
Parametric Modeling of Blurred Images for Image Restoration
British Library Conference Proceedings | 2000
|High-accuracy edge detection with Blurred Edge Model
British Library Online Contents | 2005
|