Noise-blind image deblurring

Jin, Meiguang; Roth, Stefan; Favaro, Paolo (2017). Noise-blind image deblurring. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 3834-3842). IEEE 10.1109/CVPR.2017.408

[img] Text
Jin_Noise-Blind_Image_Deblurring_CVPR_2017_paper.pdf - Published Version
Restricted to registered users only
Available under License Publisher holds Copyright.

Download (18MB) | Request a copy

We present a novel approach to noise-blind deblurring, the problem of deblurring an image with known blur, but unknown noise level. We introduce an efficient and robust solution based on a Bayesian framework using a smooth generalization of the 0-1 loss. A novel bound allows the cal- culation of very high-dimensional integrals in closed form. It avoids the degeneracy of Maximum a-Posteriori (MAP) estimates and leads to an effective noise-adaptive scheme. Moreover, we drastically accelerate our algorithm by using Majorization Minimization (MM) without introducing any approximation or boundary artifacts. We further speed up convergence by turning our algorithm into a neural network termed GradNet, which is highly parallelizable and can be efficiently trained. We demonstrate that our noise-blind for- mulation can be integrated with different priors and signifi- cantly improves existing deblurring algorithms in the noise- blind and in the known-noise case. Furthermore, GradNet leads to state-of-the-art performance across different noise levels, while retaining high computational efficiency.

Item Type:

Conference or Workshop Item (Paper)


08 Faculty of Science > Institute of Computer Science (INF) > Computer Vision Group (CVG)
08 Faculty of Science > Institute of Computer Science (INF)

UniBE Contributor:

Jin, Meiguang and Favaro, Paolo


000 Computer science, knowledge & systems
500 Science > 510 Mathematics






Xiaochen Wang

Date Deposited:

20 Apr 2018 12:39

Last Modified:

25 Oct 2019 14:00

Publisher DOI:





Actions (login required)

Edit item Edit item
Provide Feedback