基于照度与场景纹理注意力图的低光图像增强  

Low-light image enhancement algorithm based on illumination and scene texture attention map

作　　者：赵明华[1] 汶怡春 都双丽 胡静 石程 李鹏[1] Zhao Minghua;Wen Yichun;Du Shuangli;Hu Jing;Shi Cheng;Li Peng(School of Computer Science and Engineering,Xi'an University of Technology,Xi'an 710048,China)

机构地区：[1]西安理工大学计算机科学与工程学院,西安710048

出　　处：《中国图象图形学报》2024年第4期862-874,共13页Journal of Image and Graphics

基　　金：国家自然科学基金项目(61901363,52275511);陕西省自然科学基金项目(2024JC-ZDXM-35,2024JC-YBMS-458);西安碑林区应用技术研发项目(GX2244);陕西省教育厅重点实验室基金项目(20JS086)。

摘　　要：目的 现有的低照度图像增强算法常存在局部区域欠增强、过增强及色彩偏差等情况,且对于极低照度图像增强,伴随着噪声放大及细节信息丢失等问题。对此,提出了一种基于照度与场景纹理注意力图的低光图像增强算法。方法 首先,为了降低色彩偏差对注意力图估计模块的影响,对低光照图像进行了色彩均衡处理;其次,试图利用低照度图像最小通道约束图对正常曝光图像的照度和纹理进行注意力图估计,为后续增强模块提供信息引导;然后,设计全局与局部相结合的增强模块,用获取的照度和场景纹理注意力估计图引导图像亮度提升和噪声抑制,并将得到的全局增强结果划分成图像块进行局部优化,提升增强性能,有效避免了局部欠增强和过增强的问题。结果 将本文算法与2种传统方法和4种深度学习算法比较,主观视觉和客观指标均表明本文增强结果在亮度、对比度以及噪声抑制等方面取得了优异的性能。在VV(Vasileios Vonikakis)数据集上,本文方法的BTMQI(blind tone-mapped quality index)和NIQMC(no-reference image quality metric for contrast distortion)指标均达到最优值;在178幅普通低照度图像上本文算法的BTMQI和NIQMC均取得次优值,但纹理突出和噪声抑制优势显著。结论 大量定性及定量的实验结果表明,本文方法能有效提升图像亮度和对比度,且在突出暗区纹理时,能有效抑制噪声。本文方法用于极低照度图像时,在色彩还原、细节纹理恢复和噪声抑制方面均具有明显优势。代码已共享在Github上:https://github.com/shuanglidu/LLIE_CEIST.git。Objective Owing to the lack of sufficient environmental light,images captured from low-light scenes often suf-fer from several kinds of degradations,such as low visibility,low contrast,intensive noise,and color distortion.Such degradations will not only lower the visual perception quality of the images but also reduce the performance of the subsequent middle-and high-level vision tasks,such as object detection and recognition,semantic segmentation,and automatic driving.Therefore,the images taken under low-light conditions should be enhanced to meet subsequent utilization.Low-light image enhancement is one of the most important low-level vision tasks,which aims at improving the illumination and recovering image details of dark regions with lighting noise and has been intensively studied.Many impressive traditional methods and deep learning-based methods have been proposed.The methods achieved by traditional image processing techniques mainly include value mapping(such as histogram equalization and gamma correction)and model-based methods(such as Retinex model and atmospheric scattering model).However,they only improve image quality from a single perspective,such as contrast or dynamic range,and neglect such degradations as noise and scene detail recovery.On the contrary,with the great development of deep neural networks in low-level computer vision,deep learning-based methods can simultaneously optimize the enhancement results from multiple perspectives,such as brightness,color,and contrast.Thus,the enhancement performance is significantly improved.Although significant progress has been achieved,the existing deep learning-based enhancement methods have drawbacks,such as underenhancement,overenhancement,and color distortion in local areas,and the enhanced results are inconsistent with the visual characteristics of human eyes.In addition,given the high distortion degree of extremely low-light images,recovering scene details and suppressing noise amplification during enhancement are usually difficult.Therefore,increa

关 键 词：低照度图像增强 注意力机制 U-Net网络 照度估计 最小通道约束图 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]