Translator Disclaimer
2 November 2018 Self-augmented deep generative network for blind image deblurring
Author Affiliations +
Image deblurring is a challenging ill-posed problem in computer vision. In this paper, we propose two endto- end generative networks to solve the problem of blind image deblurring and blurring. We chain them together to enhance each other constantly, which means that the output of the one generator is delivered to the another and a more realistic and relevant output is expected. We propose the deblur generator to generate sharp images from blur ones, which is what exactly we want in blind image deblurring. We also propose the self augmented block to enhance the performance of the generative network. Every generative filter is also associated with its own discriminator to compose a conditional GAN to promote the result of the generator. Additionally, to emphasize the edges of the image on the deblur generator, we use reconstructed loss to constrain the generator. The experiments on the benchmark datasets prove the effective of the deblur generator against state-of-the-art algorithms both quantitatively and qualitatively.
© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Ke Peng, Zhiguo Jiang, and Haopeng Zhang "Self-augmented deep generative network for blind image deblurring", Proc. SPIE 10817, Optoelectronic Imaging and Multimedia Technology V, 108170M (2 November 2018);


CAGD-Based Computer Vision
Proceedings of SPIE (August 22 1988)
Circle Parameter Estimation From Partial Arcs
Proceedings of SPIE (March 27 1989)
Robust parallel clustering algorithm for image segmentation
Proceedings of SPIE (February 27 1996)
Dynamic surfaces
Proceedings of SPIE (November 01 1992)
Locating Fast Moving Objects In TV Images In The Presence...
Proceedings of SPIE (October 26 1983)

Back to Top