基于多曝光的高动态图像合成的噪声处理

针对在高动态范围图像合成的过程中有噪声影响图像的质量这一问题,采取一种基于多曝光图像的高动态范围图像合成降噪算法。通过对各曝光图像的灰度数据进行提取、整理、分析,能合成代表原始场景光线分布的亮度图像。通过分析噪声对高动态范围图像合成质量的影响,提出在图像合成前将图像中含有的噪声进行处理。根据光子散粒噪声变化的特点,将图像混有的噪声问题转化为求解一个多曝光图像序列组的平均值问题,合成的图像视觉效果与真实图像极为接近。     

一种改进的基于小波域的多曝光图像融合算法

自然界光照强度的动态范围较宽,而普通相机的动态范围远远达不到,因此,导致拍摄的图像中存在某些区域过度曝光和曝光不足,造成图像质量欠佳.文中提出了一种改进的基于小波多分辨率分析的多曝光图像融合算法以解决上述问题.首先对同一场景的多幅不同曝光图像分别进行小波变换;接着,对低频分量平均加权,获取图像近似部分的融合分量,并对高频分量基于区域方差确定权重系数,继而加权平均获取细节部分的融合分量;最后,小波逆变换获得较好质量的多曝光融合图像.仿真实验表明,该算法在较好保持原始图像信息的情况下丰富了细节信息,并且不受曝光问题的干扰,融合了多幅不同曝光图像的优质信息,避免了时域融合过程中出现的色差现象.     

基于动态场景的高动态图像合成

相机所取得的图像动态范围与真实的场景相比往往较低。而通过对几幅不同的曝光时间的图像进行合成,可以得到高动态图像。但是场景中物体的运动会导致最终图像出现鬼影效应,提出了一个基于区域分割和连续性检测的算法,消除鬼影区域,使得在场景有运动下同样可以获得高质量的高动态图像。     

动态场景下深度自监督多曝光图像融合方法

近年来,面向动态场景的多曝光图像融合技术取得重大进展.其中,基于深度学习的方法在视觉效果和运算效率上都远超传统算法,成为高动态范围成像技术的主流.然而,现有基于深度学习的融合方法都以有监督学习的方式实现,过度依赖真值图像,难以被广泛应用于实际场景中.本文提出了一个基于深度自监督学习的动态多曝光图像融合网络,主要贡献包括：设计自监督的动态多曝光融合网络框架,探索高动态范围图像与低动态范围图像序列的内在关联;提出基于注意力机制的全局去伪影模块,使用全局文本模块减少动态融合产生的运动伪影,增强图像细节;提出融合重建模块,通过残差和稠密连接实现多层次特征之间的信息流动;设计运动掩膜引导的自监督损失函数,用于网络的高效训练.实验表明,与现有方法相比,本文提出的方法在高动态范围图像重建的主观和客观质量上均表现较好,运算效率显著提升.     

基于深度学习的岩石薄片正交偏光图像多曝光融合算法

针对正交偏光下岩石薄片图像中动态范围较低,无法观察全部颗粒的问题,将深度学习应用于多曝光图像融合算法,通过融合多个曝光度的薄片图像来获取较高的动态范围。首先将低动态范围的多曝光图像序列输入卷积神经网络,然后网络通过优化损失函数获取较好的权重图预测结果,最后由源多曝光图像序列联合权重图加权融合得到具有较高动态范围的薄片图像。对比实验表明,该算法可以有效地提升图像中的颗粒清晰度。     

高质量的虚拟视点图像的绘制方法

针对应用深度图像的绘制(DIBR)技术生成的虚拟视点图像中存在的空洞问题,提出了一种基于DIBR的高质量的虚拟视点图像绘制算法.先由多幅参考图像分别生成同一虚拟视点位置的多幅目标图像,将这些虚拟视点目标图像融合为含有少量空洞的目标图像.然后采用逆映射的方法在多幅参考图像中找到这些剩余少量空洞的对应内容并填充空洞,从而生成高质量的虚拟视点图像.实验结果表明最后生成的虚拟视点图像具有良好的视觉效果.     

面向虚拟视点图像绘制的深度图编码算法

针对不同区域对绘制虚拟视点图像质量产生不同的影响,以及深度估计不准确导致时域抖动效应影响压缩效率的问题,提出了一种面向虚拟视点图像绘制的深度图压缩算法。通过彩色图像帧差、深度图边缘提取等相关处理过程,提取深度图的静态区域、边缘区域以及动态区域。对深度图边缘区域使用了较低的量化系数,以提高深度图边缘区域编码质量;根据深度图各个区域的编码模式特点,仅对部分编码模式而不是所有模式进行率失真优化搜索,以提高深度图的编码速度;对于深度图P帧的静态区域,合理地采用了SKIP模式,以消除由于深度估计算法的局限性导致时域抖动效应对深度图压缩的影响。实验结果表明,与传统的H.264编码方案相比,本文方案在传输码流大小基本不变的前提下提高了最终虚拟视点图像边缘区域的绘制质量,其余区域主观质量相近,而深度图编码时间则节省了约77～87%。     

交互式立体显示中基于图像拼合的视点合成

在立体显示中,视点合成是实现交互性的关键技术,即在三维(3D)场景中通过自由选择视点而获得环视能力.本文将视点插值和基于图像拼合的视点变形技术相结合,提出一种中间视合成算法.首先均匀化原始立体图像对;然后只对前景对象区域进行视差估计以提高视差匹配的速度和精度;接着确定左右视点中的可靠区域,根据可靠区域生成过渡中间视点;最后,采用视点插值结合变形的方法,由过渡视合成中间视点.实验结果表明合成的中间视点图像质量良好,而且合成速度也明显提高.本文算法可用于实时 3D 视频应用的交互式立体显示,可以实现任意视点的实时绘制.     

构造全局背景的虚拟视点合成算法

虚拟视点合成技术是三维电视、多视点视频等诸多领域中的关键技术。目前,基于深度图像的绘制(DIBR)受到了广泛的关注,而这一技术的主要难点在于如何降低映射过程中产生的空洞。为解决这个问题,提高合成图像的质量,同时降低所需参考视点的数量,本文提出了一种基于全局背景图像的虚拟视点合成算法。首先,我们利用视频序列的帧间互补信息生成一张全局背景图像,并以此为辅助图像,去填补从参考视点映射到虚拟目标视点的各帧图像。与传统方法相比,本文算法能使用空洞区域对应的真实像素进行填充,提高了图像的质量。最后,对填补后仍余留的空洞采用图像修复算法进行处理,得到最终的虚拟视点图像。实验结果表明,这个算法优于传统算法,并且只利用了一个参考视点。      

基于权重最小二乘结构边缘保持色调映射算法

高动态范围图像由于其动态范围超过普通显示器的动态范围,所以无法正常显示,从而需要研究在保留高动态范围图像对比度、细节信息以及色彩信息的情况下压缩高动态范围图像的动态范围以适应低动态范围显示器进行显示的色调映射算法。本文提出基于权重最小二乘结构的边缘保持图像平滑色调映射算法。首先,建立基于权重最小二乘的边缘保持图像平滑滤波算子;然后,将输入的高动态范围图像转换至NTSC空间分离亮度信息和颜色信息,利用该滤波算子对亮度信息进行多级分层,获得基本层以及多级细节层信息;最后,对基本层进行动态范围压缩,利用压缩后的基本层结合多级细节层信息并转换回RGB空间获得输出的低动态范围图像。文中通过实验采集的多曝光图像序列利用Debevec和Malik提出高动态范围图像融合算法获得拍摄场景的高动态范围图像,采用本文提出算法对高动态范围图像进行色调映射处理获得较为理想的保留图像有效信息的低动态范围图像,从而验证了文中提出算法的有效性。     

Rate–distortion optimization of multi-exposure image coding for high dynamic range image coding

High dynamic range (HDR) images have many practical applications because they offer an extended dynamic range and a more realistic visual experience. A HDR image is usually stored in floating-point format, so pre-processing is required to make the HDR image compatible with coding standards. A transfer function is also used to achieve better coding efficiency. Typically, HDR images are generated using several low dynamic range (LDR) images with different exposures. Instead of compressing the HDR image when it is generated from images with multiple exposures, this study proposes a technique to compress the multi-exposure images. The HDR image generation, as well as the multi-exposure images fusion, can be realized in the decoder. The proposed framework encodes the multi-exposure images using MV-HEVC where the inter-view redundancy is well exploited when an accurate intensity-mapping function between the multi-exposure images has been established. Multi-exposure image coding is used to produce a high-quality HDR image so the rate–distortion optimization (RDO) is modified by considering both the reconstruction quality of the current block and its effect on the multi-exposure fused image. A Lagrange multiplier is modified to maintain a balance between the rate and the modified distortion during the RDO process. Compared to encoding the generated HDR image using HEVC range extension, the experimental results show that the proposed technique achieves significant bitrate savings for equivalent quality in terms of HDR-VDP-2.     

Geometric and colorimetric error compensation for multi-view images

In general, excessive colorimetric and geometric errors in multi-view images induce visual fatigue to users. Various works have been proposed to reduce these errors, but conventional works have only been available for stereoscopic images while requiring cumbersome additional tasks, and often showing unstable results. In this paper, we propose an effective multi-view image refinement algorithm. The proposed algorithm analyzes such errors in multi-view images from sparse correspondences and compensates them automatically. While the conventional works transform every view to compensate geometric errors, the proposed method transforms only the source views with consideration of a reference view. Therefore this approach can be extended regardless of the number of views. In addition, we also employ uniform view intervals to provide consistent depth perception among views. We correct color inconsistency among views from the correspondences by considering importance and channel properties. Various experimental results show that the proposed algorithm outperforms conventional approaches and generates more visually comfortable multi-view images.     

Blind quality assessment of tone-mapped images using multi-exposure sequences

The tone mapping operator (TMO) enables high dynamic range (HDR) images to be presented on low dynamic range (LDR) consumer electronic devices. However, the results obtained by this method are not always ideal due to the reduced number of bits. In comparison, the multi-exposure image fusion (MEF) bypasses the intermediate HDR image composition and directly produces an image presented on standard devices. Inspired by this, this paper proposes a quality assessment method for tone-mapped image (TMI) based on generating multi-exposure sequences. Specifically, the method uses a generative adversarial network (GAN) to generate a set of sequences with different exposure levels based on the TMIs. Then a two-branch convolutional neural network (CNN) is used to extract features from the tone-mapped images and the multi-exposure reference sequences, respectively. Finally, the transformer is used to mine the intrinsic connections between TMIs and multi-exposure sequences and learn the mapping relationships from feature space to quality space. We conducted extensive experiments on the ESPL-LIVE HDR database. The applicability and effectiveness of the proposed method are verified by comparing and analyzing relevant features and model configurations with existing mainstream evaluation algorithms.     

梯度域多曝光图像融合

为解决多曝光图像融合的问题,提出了一种新颖的直接将多曝光图像融合成适合显示的低动态范围图像的方法,并且具备消除运动伪影的能力。使用联合柱状图探究两幅图像之间像素值的对应关系,对每幅图像检测分别得到一幅伪影权值图,用来构造融合时的度量。在梯度域中进行融合,根据多维黎曼流形几何(Riemannian Geometry),从多个输入图像的结构张量中推导得出融合的梯度域,然后使用均值滤波器在多尺度上进行梯度域的非线性修改,通过解泊松方程得到融合图像。最后,还提出了一种新颖的色彩复原算法,用以避免造成色彩偏差。实验表明,该方法能够有效融合含运动物体的多曝光图像,无论哪幅图像被选作参考图像,都能获得高质量的结果图像。该算法同时具有处理的有效性和时间的高效性。     

基于多尺度几何分析的SAR图像融合

在穿墙雷达成像技术中,建筑布局成像对确定墙后人体目标的空间相对位置以及多径虚假目标的提取有重要意义。目前的建筑布局成像一般采用多通道多视角图像融合方法,对此提出一种基于多尺度分析,即基于小波分解下的多通道多视角图像融合算法。该算法分为两个阶段,第一阶段涉及到单视角下的多通道图像融合,该阶段的融合目的主要是为增强图像细节信息和提高图像清晰度。因此对其小波分解后的图像高频分量采用平均梯度增强的加权融合算法,低频分量采用平均加权融合,后经小波反变换后形成多幅单视角图像;第二阶段涉及到多视角融合,该阶段的融合目的主要是为了增强图像的对比度,并且考虑到此阶段不同视角下图像经小波分解后的三个高频分量对比度各不相同,因此高频分量采用对比度增强的加权融合算法,低频分量仍采用平均加权融合,后将融合后的频率分量经小波反变换,便可得到一幅完整融合图像。仿真结果表明,提出的基于小波分解下的多通道多视角图像融合算法不论在图像视觉效果的改善和信噪比的提高等方面都有较大的作用。     

Virtual view synthesis using joint information from multi-view

Immersive media has attracted widespread attention with the development of virtual reality. Three Degree of Freedom Plus media greatly enhances the user experience by allowing users’ head motion and viewpoint switching within a certain range. Due to the limitation of panoramic video acquisition and transmission, it is impossible to obtain videos from any viewpoint directly. Virtual view synthesis is the general solution to this problem. However, existing algorithms do not adequately consider the pixel correlation between multiple views. Thus, we propose a virtual view synthesis algorithm using joint information from multi-view panoramic videos to further explore the pixel correlation. Specifically, sub-pixels from different reference views in the virtual view are obtained by performing multi-view three-dimensional image warping. Dedicated area division and interpolation methods are then designed to improve the synthesized quality. Experimental results show that the proposed algorithm outperforms the state-of-the-art virtual view synthesis algorithms in performance and efficiency.     

一种基于双通道CMOS相机的低照度动态场景HDR融合方法

高动态范围成像技术能够全面有效反映场景信息,有利于在高动态范围场景下获得高质量的成像。但当前常用的基于单台相机的多次曝光融合方法在动态场景下易出现“鬼影”问题,基于多个传感器同时曝光的系统复杂且价格昂贵,基于单幅低动态范围图像的拓展方法易丢失欠曝光或过曝光区域的细节信息,且多用于较好的照明条件。针对低照度动态场景成像,研究了一种基于双通道低照度CMOS相机的高动态范围图像融合方法,对双通道CMOS相机采集低照度动态场景两幅不同曝光图像,依据累计直方图拓展原则分别进行动态范围拓展,并采用像素级融合方法对动态范围拓展的序列图像进行融合。实验表明,动态范围拓展融合方法可满足低照度动态场景下获取高动态范围图像的应用要求,获得更佳的成像质量。     

High quality virtual view synthesis based on corrected surface mapping and image fusion

Perceptual errors introduced by current virtual view creation approaches for free viewpoint video often result in severe distortions in synthesised images. A novel virtual view synthesis algorithm is proposed based on corrected region based surface mapping and an image fusion method to reduce perceptual errors. The results over multi-view image sets imply that the proposed method improves the objective and subjective performance simultaneously, compared with previous dominant multiple image view synthesis approaches.