Avoiding Undesirable Solutions of Deep Blind Image Deconvolution

Antonie Brožová, Antonie Brožová, Václav Šmídl

2024

Abstract

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 from L 2 norm in loss was found to be the most successful approach to mitigate the artifacts.

Paper Citation

in Harvard Style

Brožová A. and Šmídl V. (2024). Avoiding Undesirable Solutions of Deep Blind Image Deconvolution. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP; ISBN 978-989-758-679-8, SciTePress, pages 559-566. DOI: 10.5220/0012397600003660

in Bibtex Style

@conference{visapp24,
author={Antonie Brožová and Václav Šmídl},
title={Avoiding Undesirable Solutions of Deep Blind Image Deconvolution},
booktitle={Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP},
year={2024},
pages={559-566},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012397600003660},
isbn={978-989-758-679-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP
TI - Avoiding Undesirable Solutions of Deep Blind Image Deconvolution
SN - 978-989-758-679-8
AU - Brožová A.
AU - Šmídl V.
PY - 2024
SP - 559
EP - 566
DO - 10.5220/0012397600003660
PB - SciTePress