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.
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: