Sparse Gradient Regularized Deep Retinex Network for Robust Low-Light Image Enhancement

Due to the absence of a desirable objective for low-light image enhancement, previous data-driven methods may provide undesirable enhanced results including amplified noise, degraded contrast and biased colors. In this work, inspired by Retinex theory, we design an end-to-end signal prior-guided lay...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on image processing Ročník 30; s. 1
Hlavní autoři: Yang, Wenhan, Wang, Wenjing, Huang, Haofeng, Wanga, Shiqi, Liu, Jiaying
Médium: Journal Article
Jazyk:angličtina
Vydáno: United States IEEE 01.01.2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Atmospheric modeling
denoising
Illumination
Image coding
Image compression
Image enhancement
Image restoration
Light
Lighting
Low-light enhancement
Minimization
Noise
Noise reduction
Reflectance
Regularization
residual dense network
Retinex model
sparse gradient regularization
ISSN:1057-7149, 1941-0042, 1941-0042
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Due to the absence of a desirable objective for low-light image enhancement, previous data-driven methods may provide undesirable enhanced results including amplified noise, degraded contrast and biased colors. In this work, inspired by Retinex theory, we design an end-to-end signal prior-guided layer separation and data-driven mapping network with layer-specified constraints for single-image low-light enhancement. A Sparse Gradient Minimization sub-Network (SGM-Net) is constructed to remove the low-amplitude structures and preserve major edge information, which facilitates extracting paired illumination maps of low/normal-light images. After the learned decomposition, two sub-networks (Enhance-Net and Restore-Net) are utilized to predict the enhanced illumination and reflectance maps, respectively, which helps stretch the contrast of the illumination map and remove intensive noise in the reflectance map. The effects of all these configured constraints, including the signal structure regularization and losses, combine together reciprocally, which leads to good reconstruction results in overall visual quality. The evaluation on both synthetic and real images, particularly on those containing intensive noise, compression artifacts and their interleaved artifacts, shows the effectiveness of our novel models, which significantly outperforms the state-of-the-art methods.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1057-7149
1941-0042
1941-0042
DOI:10.1109/TIP.2021.3050850