You Do Not Need Additional Priors or Regularizers in Retinex-Based Low-Light Image Enhancement
Authors:
- 1 June 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 18125-18134
Abstract
Images captured in low-light conditions often suffer from significant quality degradation. Recent works have built a large variety of deep Retinex-based networks to enhance low-light images. The Retinex-based methods require decomposing the image into reflectance and illumination components, which is a highly ill-posed problem and there is no available ground truth. Previous works addressed this problem by imposing some additional priors or regularizers. However, finding an effective prior or regularizer that can be applied in various scenes is challenging, and the performance of the model suffers from too many additional constraints. We propose a contrastive learning method and a self-knowledge distillation method for Retinex decomposition that allow training our Retinex-based model without elaborate hand-crafted regularization functions. Rather than estimating reflectance and illuminance images and representing the final images as their element-wise products as in previous works, our regularizer-free Retinex decomposition and synthesis network (RFR) extracts reflectance and illuminance features and synthesizes them end-to-end. In addition, we propose a loss function for contrastive learning and a progressive learning strategy for self-knowledge distillation. Extensive experimental results demonstrate that our proposed methods can achieve superior performance compared with state-of-the-art approaches.Keywords
This publication has 33 references indexed in Scilit:
- LLNet: A deep autoencoder approach to natural low-light image enhancementPattern Recognition, 2017
- Perceptual Quality Assessment for Multi-Exposure Image FusionIEEE Transactions on Image Processing, 2015
- Adaptive Multiscale Retinex for Image Contrast Enhancement2013
- Contrast Enhancement Based on Layered Difference Representation of 2D HistogramsIEEE Transactions on Image Processing, 2013
- Naturalness Preserved Enhancement Algorithm for Non-Uniform Illumination ImagesIEEE Transactions on Image Processing, 2013
- Contextual and Variational Contrast EnhancementIEEE Transactions on Image Processing, 2011
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004
- A multiscale retinex for bridging the gap between color images and the human observation of scenesIEEE Transactions on Image Processing, 1997
- Properties and performance of a center/surround retinexIEEE Transactions on Image Processing, 1997
- The Retinex Theory of Color VisionScientific American, 1977