Zobrazit v EDS

Applied aspects of modern non-blind image deconvolution methods

Uloženo v:
Podrobná bibliografie
Název: Applied aspects of modern non-blind image deconvolution methods
Autoři: O.B. Chaganova, A.S. Grigoryev, D.P. Nikolaev, I.P. Nikolaev
Zdroj: Компьютерная оптика, Vol 48, Iss 4, Pp 562-572 (2024)
Informace o vydavateli: Samara National Research University, 2024.
Rok vydání: 2024
Témata: non-blind image deconvolution, Information theory, QC350-467, Q350-390, Optics. Light, image deblurring, state-of-the-art methods, method robustness, non-blind deconvolution benchmarking
Popis: The focus of this paper is the study of modern non-blind image deconvolution methods and their application to practical tasks. The aim of the study is to determine the current state-of-the-art in non-blind image deconvolution and to identify the limitations of current approaches, with a focus on practical application details. The paper proposes approaches to examine the influence of various effects on the quality of restoration, the robustness of models to errors in blur kernel estimation, and the violation of the commonly assumed uniform blur model. We developed a benchmark for validating non-blind deconvolution methods, which includes datasets of ground truth images and blur kernels, as well as a test scheme for assessing restoration quality and error robustness. Our experimental results show that those neural network models lacking any pre-optimization, such as quantization or knowledge distillation, fall short of classical methods in several key properties, such as inference speed or the ability to handle different types of blur. Nevertheless, neural network models have made notable progress in their robustness to noise and distortions. Based on the results of the study, we provided recommendations for more effective use of modern non-blind image deconvolution methods. We also developed suggestions for improving the robustness, versatility and performance quality of the models by incorporating additional practices into the training pipeline.
Druh dokumentu: Article
ISSN: 2412-6179
0134-2452
DOI: 10.18287/2412-6179-co-1409
Přístupová URL adresa: https://doaj.org/article/5901ec04b6dc4c1fb5ca7af06fa79e1e
Přístupové číslo: edsair.doi.dedup.....f655017d05042cb26ff0b58a4f35f849
Databáze: OpenAIRE
Popis
Abstrakt:The focus of this paper is the study of modern non-blind image deconvolution methods and their application to practical tasks. The aim of the study is to determine the current state-of-the-art in non-blind image deconvolution and to identify the limitations of current approaches, with a focus on practical application details. The paper proposes approaches to examine the influence of various effects on the quality of restoration, the robustness of models to errors in blur kernel estimation, and the violation of the commonly assumed uniform blur model. We developed a benchmark for validating non-blind deconvolution methods, which includes datasets of ground truth images and blur kernels, as well as a test scheme for assessing restoration quality and error robustness. Our experimental results show that those neural network models lacking any pre-optimization, such as quantization or knowledge distillation, fall short of classical methods in several key properties, such as inference speed or the ability to handle different types of blur. Nevertheless, neural network models have made notable progress in their robustness to noise and distortions. Based on the results of the study, we provided recommendations for more effective use of modern non-blind image deconvolution methods. We also developed suggestions for improving the robustness, versatility and performance quality of the models by incorporating additional practices into the training pipeline.
ISSN:24126179
01342452
DOI:10.18287/2412-6179-co-1409