Retinex Image Enhancement Based on Sequential Decomposition With a Plug-and-Play Framework
Open Access
- 6 June 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 35 (10) , 14559-14572
Abstract
The Retinex model is one of the most representative and effective methods for low-light image enhancement. However, the Retinex model does not explicitly tackle the noise problem and shows unsatisfactory enhancing results. In recent years, due to the excellent performance, deep learning models have been widely used in low-light image enhancement. However, these methods have two limitations. First, the desirable performance can only be achieved by deep learning when a large number of labeled data are available. However, it is not easy to curate massive low-/normal-light paired data. Second, deep learning is notoriously a black-box model. It is difficult to explain their inner working mechanism and understand their behaviors. In this article, using a sequential Retinex decomposition strategy, we design a plug-and-play framework based on the Retinex theory for simultaneous image enhancement and noise removal. Meanwhile, we develop a convolutional neural network-based (CNN-based) denoiser into our proposed plug-and-play framework to generate a reflectance component. The final image is enhanced by integrating the illumination and reflectance with gamma correction. The proposed plug-and-play framework can facilitate both post hoc and ad hoc interpretability. Extensive experiments on different datasets demonstrate that our framework outcompetes the state-of-the-art methods in both image enhancement and denoising.Keywords
All Related Versions
Funding Information
- National Key Research and Development Program of China (2021YFE0203700, NSFC/RGC N_CUHK 415/19, ITF MHP/038/20, CRF 8730063, RGC 14300219, 14302920, 14301121)
- Chinese University of Hong Kong (CUHK) Direct Grant for Research
- Natural Science Foundation of China (61971234, 12126340, 12126304, 11501301)
- Nanjing University of Posts and Telecommunications (NUPT) through the QingLan Project for Colleges and Universities of Jiangsu Province
- Postgraduate Research and Practice Innovation Program of Jiangsu Province (SJCX21_0247)
This publication has 62 references indexed in Scilit:
- LLNet: A deep autoencoder approach to natural low-light image enhancementPattern Recognition, 2017
- Blind Quality Assessment of Tone-Mapped Images Via Analysis of Information, Naturalness, and StructureIEEE Transactions on Multimedia, 2016
- Convolutional Neural Network with Biologically Inspired ON/OFF ReLU2015
- No-Reference Image Sharpness Assessment in Autoregressive Parameter SpaceIEEE Transactions on Image Processing, 2015
- Retinex by Higher Order Total Variation $L^{1}$ L 1 DecompositionJournal of Mathematical Imaging and Vision, 2015
- Retinex image enhancement via a learned dictionaryOptical Engineering, 2015
- Weighted Nuclear Norm Minimization with Application to Image Denoising2014
- Naturalness Preserved Enhancement Algorithm for Non-Uniform Illumination ImagesIEEE Transactions on Image Processing, 2013
- A Total Variation Model for RetinexSIAM Journal on Imaging Sciences, 2011
- Analysis and extensions of the Frankle-McCann Retinex algorithmJournal of Electronic Imaging, 2004