基于双重迭代的零样本低照度图像增强

针对低光照条件下拍摄图像质量低下的问题,该文提出一种基于双重迭代的零样本低照度图像增强方法。其外层迭代通过卷积神经网络估计增强参数,再由内层迭代进行图像增强,增强结果进一步用于计算损失函数并反馈更新外层的参数估计网络,最终通过多轮迭代生成高质量的图像。在该框架下,还设计了多尺度增强系数估计模块、基于注意力的像素级大气光估计模块,并提出了基于亮度对比度、大气光、颜色均衡以及图像平滑性先验的无监督损失函数。大量实验结果表明,该方法可有效将低光照图像增强为高质量的清晰图像,其性能优于现有的同类方法。同时该方法基于零样本学习,不需任何训练数据集,具有良好的普适性。     

基于深度学习的低照度图像增强方法

在低照度环境下采集的图像往往亮度不足,导致在后续视觉任务中难以有效利用.针对这一问题,过去的低照度图像增强方法大多在极度低光场景中表现失败,甚至放大了图像中的底层噪声.为了解决这一难题,本文提出了 一种新的基于深度学习的端到端神经网络,该网络主要通过空间和通道双重注意力机制来抑制色差和噪声,其中空间注意力模块利用图像的...     

基于无监督学习的双分支融合低光图像增强方法

针对经过算法增强后的图像产生伪影且图像噪声放大的问题,提出了一种基于无监督学习的双路融合低光照图像增强网络(Unsupervised Learning-based Dual Fusion Low-light Image Enhancement Network, ULDFNet),可从非配对的低光和正常光数据集中学习到低光图像到正常光图像的映射方式。ULDFNet由双支路构成,上支路是注重对噪声进行抑制的细化分支,下支路是基于注意力机制的U-Net全局重建分支,用于高质量图像的生成。判别网络采用特征金字塔的多尺度结构来增强图像全局一致性,同时改进了损失函数,引入全新的保真度循环一致性损失来进一步提高图像纹理信息的恢复质量。定性与定量的实验结果证明了所提方法能够有效抑制增强后图像伪影的产生和噪声的放大。     

基于深度学习的低照度图像增强技术研究综述

使用图像增强方法和深度学习的方法可以提高低照度图像亮度,改善图像质量.文章首先对传统的低照度图像增强算法分类介绍,总结这些算法近年来的改进过程,然后重点介绍当下适用于低照度图像增强的网络模型,同时对这些网络结构和适用于该网络的部分方法进行梳理,最后介绍实验所需要的数据库与增强后图像的评价准则,提出了目前深度学习在该领域...     

基于Retinex的低照度图像增强

Retinex理论是颜色恒常知觉的计算理论,可以用于图像清晰度严重失真状况下的图像增强.在研究Retinex算法的基础上,对低照度彩色图像失真中色彩恢复存在的问题进行研究,构建了一个恢复效果较好的色彩恢复函数——余弦色彩恢复函数.给出了处理后图像的自动补偿/增益方法以及补偿/增益中参数实际选取的经验值.对处理后的图像进行了质量评价分析,表明该恢复函数在处理低照度图像时具有较明显的改善效果.     

基于改进Retinex算法的低照度图像增强

通过对比不同图像增强算法,针对传统图像增强算法无法兼顾色彩、细节以及纹理的同步处理等问题,文章提出一种MSRCR-HIS图像增强算法,融合直方图转换法与MSRCR算法的优势,并将处理后的图像与原始图像进行融合以保留原图细节信息,通过验证,文章提出的算法与经典算法相比,能够有效地改善图像的呈现效果,有利于后续各项实验操作。     

基于任务解耦的低照度图像增强方法

低照度条件下拍摄的照片往往存在亮度低、颜色失真、噪声高、细节退化等多重耦合问题,因此低照度图像增强是一个具有挑战性的任务.现有基于深度学习的低照度图像增强方法通常聚焦于对亮度和色彩的提升,导致增强图像中仍然存在噪声等缺陷.针对上述问题,本文提出了一种基于任务解耦的低照度图像增强方法,根据低照度图像增强任务对高层和低层特征的不同需求,将该任务解耦为亮度与色彩增强和细节重构两组任务,进而构建双分支低照度图像增强网络模型（Two-Branch Low-light Image Enhancement Network,TBLIEN）.其中,亮度与色彩增强分支采用带全局特征的U-Net结构,提取深层语义信息改善亮度与色彩;细节重构分支采用保持原始分辨率的全卷积网络实现细节复原和噪声去除.此外,在细节重构分支中,本文提出一种半双重注意力残差模块,能在保留上下文特征的同时通过空间和通道注意力强化特征,从而实现更精细的细节重构.在合成和真实数据集上的广泛实验表明,本文模型的性能超越了当前先进的低照度图像增强方法,并具有更好的泛化能力,且可适用于水下图像增强等其他图像增强任务.     

低照度短波红外图像增强算法

为了拓展非制冷短波红外探测器在弱光夜视观测方面的应用,开展了针对短波红外低照度成像的研究。提出了一种新的图像增强方法抑制图像噪声增强图像细节进而改善图像质量。使用3D降噪（3DNR（3D Noise reduction））算法,将多尺度高斯差分法结合边缘保持滤波器最大限度的分离图像高频信息与隐藏噪声,再针对图像进行自适应灰度映射。实验结果表明：该算法显著地抑制了在低照度下图像的时域噪声,丰富了短波红外图像的细节,改善了短波红外的夜视显示效果。     

基于并联残差网络的低照度图像增强算法

为了解决低照度图像亮度低、对比度低、信息丢失严重、颜色失真等问题,提出一种基于并联残差网络的低照度图像增强算法.该网络模型的主要思想是将交替残差模块与局部全局残差模块进行并联,运用改进的损失函数计算测试集损失,不断地调整网络参数,最终得到具有较强增强能力的网络模型.实验结果表明,本文网络模型能够有效提高图像亮度、对比度...     

Low-light color image enhancement based on NSST

In order to improve the visibility and contrast of low-light images and better preserve the edge and details of images, a new low-light color image enhancement algorithm is proposed in this paper. The steps of the proposed algorithm are described as follows. First, the image is converted from the red, green and blue (RGB) color space to the hue , saturation and value (HSV) color space, and the histogram equalization (HE) is performed on the value component. Next, non-subsampled shearlet transform (NSST) is used on the value component to decompose the image into a low frequency sub-band and several high frequency sub-bands. Then, the low frequency sub-band and high frequency sub-bands are enhanced respectively by Gamma correction and improved guided image filtering (IGIF), and the enhancedvalue component is formed by inverse NSST transform. Finally, the image is converted back to the RGB color space to obtain the enhanced image. Experimental results show that the proposed method not only significantly improves the visibility and contrast, but also better preserves the edge and details of images.     

基于在线估计的视觉SLAM低光照图像增强算法

为了提升基于特征点的双目视觉定位算法在低光照环境下定位的准确性,提出一种基于在线估计的视觉同步定位与地图构建(simultaneous localization and mapping,SLAM)低光照图像增强算法.通过在线估计图像亮度值,实时更新图像增强算法的参数,解决了基于固定参数的图像增强算法在图像较亮、较暗等情...     

Low-light image enhancement network based on multi-stream information supplement

Images captured under low-light conditions often suffer from severe loss of structural details and color; therefore, image-enhancement algorithms are widely used in low-light image restoration. Image-enhancement algorithms based on the traditional Retinex model only consider the change in the image brightness, while ignoring the noise and color deviation generated during the process of image restoration. In view of these problems, this paper proposes an image enhancement network based on multi-stream information supplement, which contains a mainstream structure and two branch structures with different scales. To obtain richer feature information, an information complementary module is designed to realize the information supplement for the three structures. The feature information from the three structures is then concatenated to perform the final image recovery operation. To restore more abundant structures and realistic colors, we define a joint loss function by combining the L1 loss, structural similarity loss, and color-difference loss to guide the network training. The experimental results show that the proposed network achieves satisfactory performance in both subjective and objective aspects.

     

Low-light image enhancement via deep Retinex decomposition and bilateral learning

Low-light images enhancement is a challenging task because enhancing image brightness and reducing image degradation should be considered simultaneously. Although existing deep learning-based methods improve the visibility of low-light images, many of them tend to lose details or sacrifice naturalness. To address these issues, we present a multi-stage network for low-light image enhancement, which consists of three sub-networks. More specifically, inspired by the Retinex theory and the bilateral grid technique, we first design a reflectance and illumination decomposition network to decompose an image into reflectance and illumination maps efficiently. To increase the brightness while preserving edge information, we then devise an attention-guided illumination adjustment network. The reflectance and the adjusted illumination maps are fused and refined by adversarial learning to reduce image degradation and improve image naturalness. Experiments are conducted on our rebuilt SICE low-light image dataset, which consists of 1380 real paired images and a public dataset LOL, which has 500 real paired images and 1000 synthetic paired images. Experimental results show that the proposed method outperforms state-of-the-art methods quantitatively and qualitatively.     

Low-light image enhancement algorithm using a residual network with semantic information

Aiming to solve the poor performance of low illumination enhancement algorithms on uneven illumination images, a low-light image enhancement(LIME) algorithm based on a residual network was proposed. The algorithm constructs a deep network that uses residual modules to extract image feature information and semantic modules to extract image semantic information from different levels. Moreover, a composite loss function was also designed for the process of low illumination image enhancement, which ...     

Low-light image enhancement based on Retinex theory and dual-tree complex wavelet transform

In order to enhance the contrast of low-light images and reduce noise in them, we propose an image enhancement method based on Retinex theory and dual-tree complex wavelet transform (DT-CWT). The method first converts an image from the RGB color space to the HSV color space and decomposes the V-channel by dual-tree complex wavelet transform. Next, an improved local adaptive tone mapping method is applied to process the low frequency components of the image, and a soft threshold denoising algorithm is used to denoise the high frequency components of the image. Then, the V-channel is rebuilt and the contrast is adjusted using white balance method. Finally, the processed image is converted back into the RGB color space as the enhanced result. Experimental results show that the proposed method can effectively improve the performance in terms of contrast enhancement, noise reduction and color reproduction.     

基于CLAHE的红外图像增强算法

针对原始红外图像信息在压缩转换中数据信息丢失或弱化的问题,提出一种基于CLAHE(对比度受限自适应直方图均衡)的红外图像增强算法。该算法首先对14位原始红外图像的像素灰度级进行调整,然后通过CLAHE算法获得基图像,再通过原始图像与双边滤波后图像的差值获得细节图像,进一步通过高斯滤波算法滤除细节图像的噪声,最后合成得到输出图像。仿真结果显示:通过该算法,原始图像的对比度及边缘细节信息得到很大程度的增强。本文算法的图像增强效果优于PE算法和CLAHE算法。     

一种新的基于图像增强的融合算法

针对一般融合算法在图像预处理上存在的不足,将图像融合引入图像预处理中,使待融合图像不仅得到增强,且不损失其他信息,为下一步图像融合奠定良好的基础,在此基础上对图像进行融合,其标准差、平均梯度、熵等图像评价指标都优于直接对图像进行融合,达到预期效果.     

Low-light image enhancement by diffusion pyramid with residuals

With the advancement of the camera-related technology in mobile devices, the vast amount of photos have been taken and shared in our daily life. However, many users still have unsatisfactory experiences with low-visible photos, which are frequently acquired under complicated real-world environments. In this paper, a novel yet simple method for low-light image enhancement has been proposed without any learning procedure. The key idea of the proposed method is to estimate properties of the scene illumination both in global and local manner by exploiting the diffusion pyramid with residuals. Specifically, the residual of each scale level in the diffusion pyramid is combined with the corresponding input. This restored result efficiently highlights local details across different scale spaces, thus it is helpful for preserving the boundary of illuminations. By conducting max-pooling with restored results from different levels of the diffusion pyramid, which are resized to the original resolution, the illumination component is accurately inferred from a given image. Compared to recent learning-based approaches, one important advantage of the proposed method is to effectively avoid the overfitting problem to the specific training dataset. Experimental results on various benchmark datasets demonstrate the efficiency and robustness of the proposed method for low-light image enhancement in real-world scenarios.