ClassLIE: Structure- and Illumination-Adaptive Classification for Low-Light Image Enhancement
- 27 May 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 5 (9) , 4765-4775
Abstract
Low-light images often suffer from limited visibility and multiple types of degradation, rendering low-light image enhancement (LIE) a non-trivial task. Some endeavors have been made to enhance low-light images using convolutional neural networks (CNNs). However, they have low efficiency in learning the structural information and diverse illumination levels at the local regions of an image. Consequently, the enhanced results are affected by unexpected artifacts, such as unbalanced exposure, blur, and color bias. This paper proposes a novel framework, called ClassLIE, that combines the potential of CNNs and transformers. It classifies and adaptively learns the structural and illumination information from the low-light images in a holistic and regional manner, thus showing better enhancement performance. Our framework first employs a structure and illumination classification (SIC) module to learn the degradation information adaptively. In SIC, we decompose an input image into an illumination map and a reflectance map. A class prediction block is then designed to classify the degradation information by calculating the structure similarity scores on the reflectance map and mean square error on the illumination map. As such, each input image can be divided into patches with three enhancement difficulty levels. Then, a feature learning and fusion (FLF) module is proposed to adaptively learn the feature information with CNNs for different enhancement difficulty levels while learning the long-range dependencies for the patches in a holistic manner. Experiments on five benchmark datasets consistently show our ClassLIE achieves new state-of-the-art performance, with 25.74 PSNR and 0.92 SSIM on the LOL dataset.Keywords
This publication has 53 references indexed in Scilit:
- Exploring a radically new exponential Retinex model for multi-task environmentsJournal of King Saud University Computer and Information Sciences, 2023
- DSE-Net: Deep simultaneous estimation network for low-light image enhancementJournal of Visual Communication and Image Representation, 2023
- Smart farming using artificial intelligence: A reviewEngineering Applications of Artificial Intelligence, 2023
- Illumination estimation for nature preserving low-light image enhancementThe Visual Computer, 2023
- Low-light image enhancement by diffusion pyramid with residualsJournal of Visual Communication and Image Representation, 2021
- Beyond Brightening Low-light ImagesInternational Journal of Computer Vision, 2021
- LLNet: A deep autoencoder approach to natural low-light image enhancementPattern Recognition, 2017
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Classification of tea grains based upon image texture feature analysis under different illumination conditionsJournal of Food Engineering, 2013
- The Retinex Theory of Color VisionScientific American, 1977