Unsupervised low-light image enhancement with self-paced learning

Luo, Yu, Chen, Xuanrong, Ling, Jie, Huang, Chao, Zhou, Wei and Yue, Guanghui 2024. Unsupervised low-light image enhancement with self-paced learning. IEEE Transactions on Multimedia

Preview

PDF - Accepted Post-Print Version Available under License Creative Commons Attribution. Download (11MB) | Preview

Abstract

Low-light image enhancement (LIE) aims to restore images taken under poor lighting conditions, thereby extracting more information and details to robustly support subsequent visual tasks. While past deep learning (DL)-based techniques have achieved certain restoration effects, these existing methods treat all samples equally, ignoring the fact that difficult samples may be detrimental to the network’s convergence at the initial training stages of network training. In this paper, we introduce a selfpaced learning (SPL)-based LIE method named SPNet, which consists of three key components: the feature extraction module (FEM), the low-light image decomposition module (LIDM), and a pre-trained denoise module. Specifically, for a given low-light image, we first input the image, its pseudo-reference image, and its histogram-equalized version into the FEM to obtain preliminary features. Second, to avoid ambiguities during the early stages of training, these features are then adaptively fused via an SPL strategy and processed for retinex decomposition via LIDM. Third, we enhance the network performance by constraining the gradient prior relationship between the illumination components of the images. Finally, a pre-trained denoise module reduces noise inherent in LIE. Extensive experiments on nine public datasets reveal that the proposed SPNet outperforms eight stateof- the-art DL-based methods in both qualitative and quantitative evaluations and outperforms three conventional methods in quantitative assessments.

Item Type:	Article
Status:	In Press
Schools:	Computer Science & Informatics
Publisher:	Institute of Electrical and Electronics Engineers
ISSN:	1520-9210
Date of First Compliant Deposit:	11 September 2024
Date of Acceptance:	29 August 2024
Last Modified:	07 Nov 2024 18:30
URI:	https://orca.cardiff.ac.uk/id/eprint/172046

Actions (repository staff only)

Edit Item