Cargando…

Low-Light Image Enhancement via Retinex-Style Decomposition of Denoised Deep Image Prior

Low-light images are a common phenomenon when taking photos in low-light environments with inappropriate camera equipment, leading to shortcomings such as low contrast, color distortion, uneven brightness, and high loss of detail. These shortcomings are not only subjectively annoying but also affect...

Descripción completa

Detalles Bibliográficos
Autores principales: Gao, Xianjie, Zhang, Mingliang, Luo, Jinming
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9332408/
https://www.ncbi.nlm.nih.gov/pubmed/35898096
http://dx.doi.org/10.3390/s22155593
_version_ 1784758639373844480
author Gao, Xianjie
Zhang, Mingliang
Luo, Jinming
author_facet Gao, Xianjie
Zhang, Mingliang
Luo, Jinming
author_sort Gao, Xianjie
collection PubMed
description Low-light images are a common phenomenon when taking photos in low-light environments with inappropriate camera equipment, leading to shortcomings such as low contrast, color distortion, uneven brightness, and high loss of detail. These shortcomings are not only subjectively annoying but also affect the performance of many computer vision systems. Enhanced low-light images can be better applied to image recognition, object detection and image segmentation. This paper proposes a novel RetinexDIP method to enhance images. Noise is considered as a factor in image decomposition using deep learning generative strategies. The involvement of noise makes the image more real, weakens the coupling relationship between the three components, avoids overfitting, and improves generalization. Extensive experiments demonstrate that our method outperforms existing methods qualitatively and quantitatively.
format Online
Article
Text
id pubmed-9332408
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-93324082022-07-29 Low-Light Image Enhancement via Retinex-Style Decomposition of Denoised Deep Image Prior Gao, Xianjie Zhang, Mingliang Luo, Jinming Sensors (Basel) Communication Low-light images are a common phenomenon when taking photos in low-light environments with inappropriate camera equipment, leading to shortcomings such as low contrast, color distortion, uneven brightness, and high loss of detail. These shortcomings are not only subjectively annoying but also affect the performance of many computer vision systems. Enhanced low-light images can be better applied to image recognition, object detection and image segmentation. This paper proposes a novel RetinexDIP method to enhance images. Noise is considered as a factor in image decomposition using deep learning generative strategies. The involvement of noise makes the image more real, weakens the coupling relationship between the three components, avoids overfitting, and improves generalization. Extensive experiments demonstrate that our method outperforms existing methods qualitatively and quantitatively. MDPI 2022-07-26 /pmc/articles/PMC9332408/ /pubmed/35898096 http://dx.doi.org/10.3390/s22155593 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Communication
Gao, Xianjie
Zhang, Mingliang
Luo, Jinming
Low-Light Image Enhancement via Retinex-Style Decomposition of Denoised Deep Image Prior
title Low-Light Image Enhancement via Retinex-Style Decomposition of Denoised Deep Image Prior
title_full Low-Light Image Enhancement via Retinex-Style Decomposition of Denoised Deep Image Prior
title_fullStr Low-Light Image Enhancement via Retinex-Style Decomposition of Denoised Deep Image Prior
title_full_unstemmed Low-Light Image Enhancement via Retinex-Style Decomposition of Denoised Deep Image Prior
title_short Low-Light Image Enhancement via Retinex-Style Decomposition of Denoised Deep Image Prior
title_sort low-light image enhancement via retinex-style decomposition of denoised deep image prior
topic Communication
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9332408/
https://www.ncbi.nlm.nih.gov/pubmed/35898096
http://dx.doi.org/10.3390/s22155593
work_keys_str_mv AT gaoxianjie lowlightimageenhancementviaretinexstyledecompositionofdenoiseddeepimageprior
AT zhangmingliang lowlightimageenhancementviaretinexstyledecompositionofdenoiseddeepimageprior
AT luojinming lowlightimageenhancementviaretinexstyledecompositionofdenoiseddeepimageprior