Avoiding Undesirable Solutions of Deep Blind Image Deconvolution

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21340%2F24%3A00382635" target="_blank" >RIV/68407700:21340/24:00382635 - isvavai.cz</a>
Result on the web
<a href="http://dx.doi.org/10.5220/0012397600003660" target="_blank" >http://dx.doi.org/10.5220/0012397600003660</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.5220/0012397600003660" target="_blank" >10.5220/0012397600003660</a>

Result language
angličtina
Original language name
Avoiding Undesirable Solutions of Deep Blind Image Deconvolution
Original language description
Blind image deconvolution (BID) is a severely ill-posed optimization problem requiring additional information, typically in the form of regularization. Deep image prior (DIP) promises to model a naturally looking image due to a well-chosen structure of a neural network. The use of DIP in BID results in a significant perfor-mance improvement in terms of average PSNR. In this contribution, we offer qualitative analysis of selected DIP-based methods w.r.t. two types of undesired solutions: blurred image (no-blur) and a visually corrupted image (solution with artifacts). We perform a sensitivity study showing which aspects of the DIP-based algorithms help to avoid which undesired mode. We confirm that the no-blur can be avoided using either sharp image prior or tuning of the hyperparameters of the optimizer. The artifact solution is a harder problem since variations that suppress the artifacts often suppress good solutions as well. Switching to the structural similarity index measure fro m L2 norm in loss was found to be the most successful approach to mitigate the artifacts
Czech name
—
Czech description
—

Project
—
Continuities
I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year
2024
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP
ISBN
—
ISSN
2184-5921
e-ISSN
2184-4321
Number of pages
8
Pages from-to
559-566
Publisher name
Science and Technology Publications, Lda
Place of publication
Setúbal
Event location
Rome
Event date
Feb 27, 2024
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—

Similar results(10)