Retinex Image Enhancement Based on Sequential Decomposition With a Plug-and-Play Framework
Authors:
Preprint
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: i) 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; ii) Deep learning is notoriously a black-box model [1]. It is difficult to explain their inner-working mechanism and understand their behaviors. In this paper, using a sequential Retinex decomposition strategy, we design a plug-and-play framework based on the Retinex theory for simultaneously 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 enhanced image is produced 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
This publication has 43 references indexed in Scilit:
- CTformer: convolution-free Token2Token dilated vision transformer for low-dose CT denoisingPhysics in Medicine & Biology, 2023
- Meta Ordinal Regression Forest for Medical Image Classification With Ordinal LabelsIEEE/CAA Journal of Automatica Sinica, 2022
- Attention Guided Low-Light Image Enhancement with a Large Scale Low-Light Simulation DatasetInternational Journal of Computer Vision, 2021
- A detail preserving variational model for image RetinexApplied Mathematical Modelling, 2019
- LLNet: A deep autoencoder approach to natural low-light image enhancementPattern Recognition, 2017
- Retinex by Higher Order Total Variation $L^{1}$ L 1 DecompositionJournal of Mathematical Imaging and Vision, 2015
- Contrast Limited Adaptive Histogram Equalization image processing to improve the detection of simulated spiculations in dense mammogramsJournal of Digital Imaging, 1998
- Nonlinear image recovery with half-quadratic regularizationIEEE Transactions on Image Processing, 1995
- An alternative technique for the computation of the designator in the retinex theory of color vision.Proceedings of the National Academy of Sciences, 1986
- The Retinex Theory of Color VisionScientific American, 1977