Avoiding Undesirable Solutions of Deep Blind Image Deconvolution

Kód výsledku v 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>

Výsledek na webu

<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>

Jazyk výsledku

angličtina

Název v původním jazyce

Avoiding Undesirable Solutions of Deep Blind Image Deconvolution

Popis výsledku v původním jazyce

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

Název v anglickém jazyce

Avoiding Undesirable Solutions of Deep Blind Image Deconvolution

Popis výsledku anglicky

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

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10102 - Applied mathematics

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

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

Počet stran výsledku

8

Strana od-do

559-566

Název nakladatele

Science and Technology Publications, Lda

Místo vydání

Setúbal

Místo konání akce

Rome

Datum konání akce

27. 2. 2024

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—