Total Variation Blind Deconvolution: The Devil Is in the Details

Perrone, Daniele; Favaro, Paolo (2014). Total Variation Blind Deconvolution: The Devil Is in the Details. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 2909-2916). IEEE 10.1109/CVPR.2014.372

[img]
Preview
Text
perrone2014tv.pdf - Accepted Version
Available under License Publisher holds Copyright.

Download (12MB) | Preview
[img] Text
06909768.pdf - Published Version
Restricted to registered users only
Available under License Publisher holds Copyright.

Download (896kB)

In this paper we study the problem of blind deconvolution. Our analysis is based on the algorithm of Chan and Wong [2] which popularized the use of sparse gradient priors via total variation. We use this algorithm because many methods in the literature are essentially adaptations of this framework. Such algorithm is an iterative alternating energy minimization where at each step either the sharp image or the blur function are reconstructed. Recent work of Levin et al. [14] showed that any algorithm that tries to minimize that same energy would fail, as the desired solution has a higher energy than the no-blur solution, where the sharp image is the blurry input and the blur is a Dirac delta. However, experimentally one can observe that Chan and Wong's algorithm converges to the desired solution even when initialized with the no-blur one. We provide both analysis and experiments to resolve this paradoxical conundrum. We find that both claims are right. The key to understanding how this is possible lies in the details of Chan and Wong's implementation and in how seemingly harmless choices result in dramatic effects. Our analysis reveals that the delayed scaling (normalization) in the iterative step of the blur kernel is fundamental to the convergence of the algorithm. This then results in a procedure that eludes the no-blur solution, despite it being a global minimum of the original energy. We introduce an adaptation of this algorithm and show that, in spite of its extreme simplicity, it is very robust and achieves a performance comparable to the state of the art.

Item Type:

Conference or Workshop Item (Paper)

Division/Institute:

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

UniBE Contributor:

Perrone, Daniele, Favaro, Paolo

Subjects:

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

ISBN:

978-1-4799-5118-5

Publisher:

IEEE

Language:

English

Submitter:

Paolo Favaro

Date Deposited:

27 Apr 2015 15:23

Last Modified:

05 Dec 2022 14:45

Publisher DOI:

10.1109/CVPR.2014.372

Related URLs:

BORIS DOI:

10.7892/boris.67320

URI:

https://boris.unibe.ch/id/eprint/67320

Actions (login required)

Edit item Edit item
Provide Feedback