低照度图像增强算法研究综述  

Review of Research on Low-Light Image Enhancement Algorithms

作　　者：吕宗旺[1,2] 牛贺杰 孙福艳 甄彤[1,2] LYU Zongwang;NIU Hejie;SUN Fuyan;ZHEN Tong(School of Information Science and Engineering,Henan University of Technology,Zhengzhou 450001,China;Key Laboratory of Grain Information Processing and Control,Ministry of Education,Zhengzhou 450001,China)

机构地区：[1]河南工业大学信息科学与工程学院,河南郑州450001 [2]粮食信息处理与控制教育部重点实验室,河南郑州450001

出　　处：《红外技术》2025年第2期165-178,共14页Infrared Technology

基　　金：国家重点研发计划项目(2022YFD2100202)。

摘　　要：低照度图像增强是图像处理领域的重要问题之一,近年来,深度学习技术的迅速发展为低照度图像增强提供了新的解决方案,且具有广阔的应用前景。首先,全面分析了低照度图像增强领域的研究现状与挑战,并介绍了传统方法及其优缺点。其次,重点讨论了基于深度学习的低照度图像增强算法,根据学习策略的不同将其分为五类,分别对这些算法的原理、网络结构、解决问题进行了详细的阐述,并按时间顺序将近6年基于深度学习的图像增强代表算法进行了对比分析。接着,归纳了当前主流的数据集与评价指标,并从感知相似度和算法性能两个方面对深度学习算法进行测试评估。最后,对低照度图像增强领域改进方向与今后研究作了总结与展望。Low-light image enhancement is an important problem in the field of image processing.The rapid development of deep learning technology provides a new solution for low-light image enhancement and has broad application prospects.First,the current research status and challenges in the field of low-light image enhancement are comprehensively analyzed,and traditional methods and their advantages and disadvantages are introduced.Second,deep learning-based low-light image enhancement algorithms are classified into five categories according to their different learning strategies,and the principles,network structures,and problem-solving capabilities of these algorithms are explained in detail.Third,representative deep learning-based image enhancement algorithms from the last six years are compared and analyzed in chronological order.Fourth,the current mainstream datasets and evaluation indexes are summarized,and the deep learning algorithms are tested and evaluated in terms of perceived similarity and algorithm performance.Finally,directions for improvement and future research in the field of low-light image enhancement are discussed and suggested.

关 键 词：低照度图像 图像增强 深度学习 图像处理 低照度数据集 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]