Learning a Single Convolutional Layer Model for Low Light Image Enhancement

TL;DR

This paper introduces a highly streamlined single convolutional layer model for low-light image enhancement, utilizing structural re-parameterization and local adaptation to achieve effective results with fewer parameters.

Contribution

The paper proposes a novel single convolutional layer model with structural re-parameterization and local adaptation modules for efficient low-light image enhancement.

Findings

Performs favorably against state-of-the-art methods in objective metrics

Achieves better subjective visual quality

Has fewer parameters and lower inference complexity

Abstract

Low-light image enhancement (LLIE) aims to improve the illuminance of images due to insufficient light exposure. Recently, various lightweight learning-based LLIE methods have been proposed to handle the challenges of unfavorable prevailing low contrast, low brightness, etc. In this paper, we have streamlined the architecture of the network to the utmost degree. By utilizing the effective structural re-parameterization technique, a single convolutional layer model (SCLM) is proposed that provides global low-light enhancement as the coarsely enhanced results. In addition, we introduce a local adaptation module that learns a set of shared parameters to accomplish local illumination correction to address the issue of varied exposure levels in different image regions. Experimental results demonstrate that the proposed method performs favorably against the state-of-the-art LLIE methods in both objective metrics and subjective visual effects. Additionally, our method has fewer parameters and lower inference complexity compared to other learning-based schemes.