Paper
14 February 2020 Blind deblurring of Gaussian blurred images by blurred edge image
Yacheng Li, Lerenhan Li, Wenhao Li, Zhihua Fan, Zongmei Chen, Changxin Gao, Nong Sang
Author Affiliations +
Proceedings Volume 11430, MIPPR 2019: Pattern Recognition and Computer Vision; 1143005 (2020) https://doi.org/10.1117/12.2535530
Event: Eleventh International Symposium on Multispectral Image Processing and Pattern Recognition (MIPPR2019), 2019, Wuhan, China
Abstract
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.
© (2020) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Yacheng Li, Lerenhan Li, Wenhao Li, Zhihua Fan, Zongmei Chen, Changxin Gao, and Nong Sang "Blind deblurring of Gaussian blurred images by blurred edge image", Proc. SPIE 11430, MIPPR 2019: Pattern Recognition and Computer Vision, 1143005 (14 February 2020); https://doi.org/10.1117/12.2535530
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Network architectures

Image quality

Gallium nitride

Visualization

Convolution

Lithium

RGB color model

Back to Top