| 168 | 0 | 115 |
| 下载次数 | 被引频次 | 阅读次数 |
低光图像增强是近年来计算机视觉领域最活跃的研究方向之一。在增强过程中，会发生图像细节的丢失与噪声的增加，进而影响最终图像的品质。为解决此问题，本研究提出了一种基于Retinex理论的低光图像增强模型即RetinexNet模型。该模型由图像分解模块与亮度增强模块构成。在图像分解模块中，本研究引入了卷积块注意力模块（Convolutional Block Attention Module, CBAM）以增强网络的特征表征能力，使其聚焦于关键特征并抑制无关信息。在亮度增强模块内，设计了一个多特征融合去噪模块，以规避下采样过程中的特征丢失问题。实验结果表明，所提模型在公开数据集LOL和MIT-Adobe FiveK上的PSNR与SSIM指标均优于现有算法，同时在LIME公开数据集上亦取得了更优的NIQE指标。
Abstract：Low-light image enhancement is one of the most active research areas in the field of computer vision in recent years. In the low-light image enhancement process, loss of image details and increase in noise occur inevitably, influencing the quality of enhanced images. To alleviate this problem, a low-light image enhancement model called RetinexNet model based on Retinex theory was proposed in this study. The model was composed of an image decomposition module and a brightness enhancement module. In the decomposition module, a convolutional block attention module(CBAM) was incorporated to enhance feature representation capacity of the network, focusing on crucial features and suppressing irrelevant ones. A multifeature fusion denoising module was designed within the brightness enhancement module, circumventing the issue of feature loss during downsampling. The proposed model outperforms the existing algorithms in terms of PSNR and SSIM metrics on the publicly available datasets LOL and MIT-Adobe FiveK, as well as gives superior results in terms of NIQE metrics on the publicly available dataset LIME.
[1]LAND E H E.Lightness and Retinex Theory[J].Journal of the Optical Society of America,1971,61(1):1-11.
[2]FU X,ZENG D,HUANG Y,et al.A Fusion-Based Enhancing Method for Weakly Illuminated Images[J].Signal Processing,2016,129:82-96.
[3]GUAN Y,CHEN X A,TIAN J D,et al.Low-Light Image Enhancement Based on Multi-exposure Images Generation[J].Robot,2023,45(4):422-430.
[4]WEI C,WANG W,YANG W,et al.Deep Retinex Decomposition for Low-Light Enhancement[DB/OL].(2018-08-14)[2024-04-12].https://doi.org/10.48550/arXiv.1808.04560.
[5]DANG-NGUYEN D T,PASQUINI C,CONOTTER V,et al.Raise:A Raw Images Dataset for Digital Image Forensics[C]//Proceedings of the 6~(th)ACM Multimedia Systems Conference.2015:219-224.
[6]BYCHKOVSKY V,PARIS S,CHAN E,et al.Learning Photographic Global Tonal Adjustment with a Database of Input/Output Image Pairs[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2011:97-104.
[7]WANG S H,ZHENG J,HU H M,et al.Naturalness Preserved Enhancement Algorithm for Non-uniform Illumination Images[J].IEEE Transactions on Image Processing,2013,22(9):3538-3548.
[8]GUO X J,LI Y,LING H B.LIME:Low-Light Image Enhancement via Illumination Map Estimation[J].IEEE Transactions on Image Processing,2016,26(2):982-993.
[9]JIANG Y F,GONG X Y,LIU D,et al.EnlightenGAN:Deep Light Enhancement without Paired Supervision[J].IEEE Transactions on Image Processing,2021,30(3):2340-2349.
[10]LIU R S,MA L,ZHANG J A,et al.Retinex-Inspired Unrolling with Cooperative Prior Architecture Search for Low-Light Image Enhancement[C]//Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition.IEEE,2021:10556-10565.
[11]LI C,GUO C,LOY C C.Learning to Enhance LowLight Image via Zero-Reference Deep Curve Estimation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2021,44(8):4225-4238.
[12]ZHANG Y,ZHANG J,GUO X.Kindling the Darkness:A Practical Low-Light Image Enhancer[C]//Proceedings of the 27~(th)ACM International Conference On Multimedia.2019:1632-1640.
[13]ZAMIR S W,ARORA A,KHAN S,et al.Restormer:Efficient Transformer for High-Resolution Image Restoration[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2022:5728-5739.
基本信息:
DOI：10.19370/j.cnki.cn10-1886/ts.2025.05.002
中图分类号:TP391.41
引用信息:
[1]尚成,司占军,张滢雪.基于Retinex理论的低光图像增强模型（英文）[J].印刷与数字媒体技术研究,2025,No.238(05):14-20+57.DOI:10.19370/j.cnki.cn10-1886/ts.2025.05.002.
2025-10-10
2025-10-10