Journal of Computer Applications ›› 2024, Vol. 44 ›› Issue (6): 1911-1919.DOI: 10.11772/j.issn.1001-9081.2023060736

Special Issue: 多媒体计算与计算机仿真

• Multimedia computing and computer simulation • Previous Articles     Next Articles

Progressive enhancement algorithm for low-light images based on layer guidance

Mengyuan HUANG1, Kan CHANG1,2(), Mingyang LING1, Xinjie WEI1, Tuanfa QIN1,2   

  1. 1.School of Computer and Electronic Information,Guangxi University,Nanning Guangxi 530004,China
    2.Guangxi Key Laboratory of Multimedia Communications and Network Technology (Guangxi University),Nanning Guangxi 530004,China
  • Received:2023-06-09 Revised:2023-08-08 Accepted:2023-08-10 Online:2023-08-30 Published:2024-06-10
  • Contact: Kan CHANG
  • About author:HUANG Mengyuan, born in 1997, M. S. candidate. Her research interests include computer vision, exposure correction.
    LING Mingyang, born in 1998, Ph. D. candidate. Her research interests include super-resolution reconstruction.
    WEI Xinjie, born in 1996, M. S. candidate. His research interests include low-light image enhancement.
    QIN Tuanfa, born in 1966, Ph. D., professor. His research interests include multimedia communication, network coding, image and video retrieval.
  • Supported by:
    National Natural Science Foundation of China(62171145)

基于层间引导的低光照图像渐进增强算法

黄梦源1, 常侃1,2(), 凌铭阳1, 韦新杰1, 覃团发1,2   

  1. 1.广西大学 计算机与电子信息学院, 南宁 530004
    2.广西多媒体通信与网络技术重点实验室(广西大学), 南宁 530004
  • 通讯作者: 常侃
  • 作者简介:黄梦源(1997—),女(壮族),广西南宁人,硕士研究生,主要研究方向:计算机视觉、曝光调整
    凌铭阳(1998—),女(壮族),广西钦州人,博士研究生,主要研究方向:超分辨率重建
    韦新杰(1996—),男(壮族),广西贵港人,硕士研究生,主要研究方向:低光照图像增强
    覃团发(1966—),男,广西宾阳人,教授,博士,主要研究方向:多媒体通信、网络编码、图像和视频检索。
  • 基金资助:
    国家自然科学基金资助项目(62171145)

Abstract:

The quality of low-light images is poor and Low-Light Image Enhancement (LLIE) aims to improve the visual quality. Most of LLIE algorithms focus on enhancing luminance and contrast, while neglecting details. To solve this issue, a Progressive Enhancement algorithm for low-light images based on Layer Guidance (PELG) was proposed, which enhanced algorithm images to a suitable illumination level and reconstructed clear details. First, to reduce the task complexity and improve the efficiency, the image was decomposed into several frequency components by Laplace Pyramid (LP) decomposition. Secondly, since different frequency components exhibit correlation, a Transformer-based fusion model and a lightweight fusion model were respectively proposed for layer guidance. The Transformer-based model was applied between the low-frequency and the lowest high-frequency components. The lightweight model was applied between two neighbouring high-frequency components. By doing so, components were enhanced in a coarse-to-fine manner. Finally, the LP was used to reconstruct the image with uniform brightness and clear details. The experimental results show that, the proposed algorithm achieves the Peak Signal-to-Noise Ratio (PSNR) 2.3 dB higher than DSLR (Deep Stacked Laplacian Restorer) on LOL(LOw-Light dataset)-v1 and 0.55 dB higher than UNIE (Unsupervised Night Image Enhancement) on LOL-v2. Compared with other state-of-the-art LLIE algorithms, the proposed algorithm has shorter runtime and achieves significant improvement in objective and subjective quality, which is more suitable for real scenes.

Key words: Low-Light Image Enhancement (LLIE), Laplace Pyramid (LP), feature fusion, Convolutional Neural Network (CNN), Transformer

摘要:

低光照图像的图像质量通常较低,低光照图像增强(LLIE)旨在提高这类图像的视觉质量。针对现有的LLIE算法大多专注增强亮度和对比度、忽略细节增强的问题,提出一个基于层间引导的低光照图像渐进增强算法(PELG),兼顾图像亮度和细节增强。首先,使用拉普拉斯金字塔(LP)降低任务复杂度,提高算法效率;其次,利用各频率分量间的相关性,在低频和高频分量之间构建基于Transformer的层间引导融合模块,在各高频分量之间构建轻量级的层间引导融合模块,有效精炼金字塔较低层增强信息指导较高层处理图像,实现基于层间引导的渐进增强;最后,通过LP重建亮度均匀、细节清晰的增强图像。实验结果表明,所提算法的峰值信噪比(PSNR)在LOL(LOw-Light dataset)-v1上比DSLR(Deep Stacked Laplacian Restorer)高2.3 dB,在LOL-v2上比UNIE(Unsupervised Night Image Enhancement)高0.55 dB;与其他基于深度学习的LLIE算法相比,所提算法运行速度快,增强结果在客观和主观质量上均获得明显提升,更适用于实际场景。

关键词: 低光照图像增强, 拉普拉斯金字塔, 特征融合, 卷积神经网络, Transformer

CLC Number: