一种新的自然图像和计算机图形鉴别方法

提出一种自然图像和计算机生成图形的鉴别方法。借用模式识别中的二分类概念,采用块离散余弦变换和统计矩特征量来建立模型,以捕获自然图像和计算机生成图形的统计差异,选用支持向量机作为分类器进行训练和测试。实验结果表明,该方法具有精确度高、应用面广的优点,在自然图像和计算机生成图形的鉴别中有着广阔的前景。     

基于隐马尔可夫模型的自然图像和计算机图形的鉴别

根据自然图像和计算机图形在采集方式上的不同所导致的关联性差异,建立了基于隐马尔可夫模型的改进型特征值提取模型,选用支持向量机作为分类器进行训练和测试,对自然图像和计算机图形进行了分类.在哥伦比亚大学自然图像和计算机生成图像数据库上的实验结果表明,该方法的准确率达到98%.     

基于空域NSS的无参考图像质量评价

为了有效地度量不同失真类型的图像质量,提出一种基于自然场景统计(NSS)模型的空域无参考图像质量评价算法。该算法利用自然图像归一化亮度系数的统计特征趋向于服从广义高斯概率分布的特性,首先在空域计算自然图像的梯度,通过梯度密度选取自然图像的兴趣区域,提取兴趣区域图像统计特征,建立多元高斯分布(MVG)模型;然后对测试图像建立同样的MVG模型;最终通过计算测试图像和自然图像在统计规律上的偏差来对测试图像的质量做出评价。实验证明该算法与主观评价具有较好的一致性。     

基于二阶差分统计量的自然图像与计算机图形的鉴别

针对自然图像和计算机图形的鉴别问题,提出一种基于图像二阶差分统计量的鉴别方法.首先在HSV颜色空间提取图像及其校准图像的二阶差分信号和预测误差信号,在此基础上提取二阶差分信号的方差、峰度以及预测误差信号的1～4阶统计量,并将其作为分类特征,结合Fisher线性判别分析,实现2类图像的正确分类.实验结果表明,该方法可以有效地鉴别自然图像和计算机图形,与已有算法相比具有更高的识别率,且计算量小、易于实现.     

基于高阶累积量的图像鉴别方法仿真研究

在签别伪图像问题的研究中,随着图像处理技术的提升,计算机合成的图形越来越逼真,如何准确区分自然图像和计算机图形,成为图像认证研究的重要内容.由于利用自然图像和计算机图形在高阶统计特性上的不同的特点,提出一种新的高阶统计特征与预测误差矩阵相结合的分类鉴别方法.利用三级正交镜像滤波器(QMF)提取图像的各级分量,并求出各级分量及其预测误差矩阵的高阶累积量作为特征数据,然后利用支持向量机( SVM)进行训练和鉴别.实验结果表明对于实验所用的图像库具有99.10％的高鉴别率,能够有效鉴别自然图像和计算机图形,同时方法复杂程度较低、具有良好的鲁棒性及稳定性.     

基于隐式分段自回归模型的图像插值算法?

利用自然图像信号的分段统计稳态性可以有效地对图像信号进行建模。其分段统计稳态区域往往具有非规则的形态。采用规则窗口对图像统计稳态区域内的统计量进行估计存在较大的误差。提出一种基于概率描述的隐式分段自回归模型来刻画分段统计稳态区域形态,并基于该模型提出了一种改进的图像插值算法。实验结果表明,该方法可以较好地改善插值图像中在边缘处的模糊、振铃和噪声等瑕疵现象。     

不同分类器在图像盲取证中的表现

为了对数字拼接图像进行盲检测,提出了一种新的拼接图像的检测模型。使用图像质量评价量和统计特征量来建立模型,以得到原始图像和拼接图像之间的统计差异。选用支持向量机和人工神经网络作为分类器分别对该模型进行训练和测试,对拼接图像的盲检测进行了研究。实验结果表明,两种分类器都表现出较高的识别率,该模型在图像拼接检测中有着广阔的前景。     

一种基于亮度特征的图形图像分类方法

色彩管理中的自适应色域匹配技术，要求对不同渲染目的的图像自动分类。文中通过对图像的亮度直方图进行统计，提取了亮度级数和亮度直方图包络光滑度两个特征量，实现了一种基于该特征的图形图像分类方法，对自然照片和计算机生成图形这两种不同种类的图像进行了区分。     

基于隐式分段自回归模型的图像插值算法

利用自然图像信号的分段统计稳态性可以有效地对图像信号进行建模.其分段统计稳态区域往往具有非规则的形态.采用规则窗口对图像统计稳态区域内的统计量进行估计存在较大的误差.提出一种基于概率描述的隐式分段自回归模型来刻画分段统计稳态区域形态,并基于该模型提出了一种改进的图像插值算法.实验结果表明,该方法可以较好地改善插值图像中在边缘处的模糊、振铃和噪声等瑕疵现象.     

一种新的拼接图像检测方法*

图像的拼接检测在数字图像取证中占有重要的地位,因此引起了广泛的关注。为此,提出了一个有效的被动盲取证方法来检测拼接图像,通过提取多尺寸块离散余弦变换二维数组（MBDCT）的统计特征量和图像质量评价量（IQMs）来建立模型。选用哥伦比亚大学的图像拼接检验数据库来测试该模型,采用支持向量机（SVM）作为分类器进行训练和测试,实验结果表明新的拼接检测模型具有精确度高、应用面广的优点,在拼接检测中有很好的发展前景。     

一种基于相邻像素一致性的数码照片与计算机图形鉴别方法

愈来愈逼真的计算机图形正在颠覆人们"眼见为实"的传统观念,使人们难以分辨哪些是真实的数码照片,哪些是利用软件合成的图形.然而由于数码照片和计算机图形成像过程的不同,造成两类图像的相邻像素一致性存在较大差异.基于此认识,在HSV颜色空间提取了图像相邻像素一致性直方图特征和共生矩阵特征,对1300幅数码照片和500幅真实感计算机图形进行鉴别,识别率分别可达96%和93.9%.对视觉上难以区分的5幅数码照片和5幅计算机图形也取得了很好的识别效果.     

无人机图像拼接算法综述

无人机图像拼接是一个日益受到关注的研究领域,已经成为了照相绘图学、计算机图形学等研究的热点。首先给出了无人机图像拼接的一般步骤,重点归纳了三种特色鲜明的配准算法,然后简单阐述了图像融合的步骤和算法,最后通过归纳分析选定了适合无人机图像拼接的算法,并且展望了该领域的前景。     

On-line Free-viewpoint Video： From Single to Multiple View Rendering

In recent years, many image-based rendering techniques have advanced from static to dynamic scenes and thus become video-based rendering （VBR） methods. But actually, only a few of them can render new views on-line. We present a new VBR system that creates new views of a live dynamic scene. This system provides high quality images and does not require any background subtraction. Our method follows a plane-sweep approach and reaches real-time rendering using consumer graphic hardware, graphics processing unit （GPU）. Only one computer is used for both acquisition and rendering. The video stream acquisition is performed by at least 3 webcams. We propose an additional video stream management that extends the number of webcams to 10 or more. These considerations make our system low-cost and hence accessible for everyone. We also present an adaptation of our plane-sweep method to create simultaneously multiple views of the scene in real-time. Our system is especially designed for stereovision using autostereoscopic displays. The new views are computed from 4 webcams connected to a computer and are compressed in order to be transfered to a mobile phone. Using GPU programming, our method provides up to 16 images of the scene in real-time. The use of both GPU and CPU makes this method work on only one consumer grade computer.     

双重对偶生成对抗网络的跨年龄素描—照片转换

目的 跨年龄素描-照片转换旨在根据面部素描图像合成同一人物不同年龄阶段的面部照片图像。该任务在公共安全和数字娱乐等领域具有广泛的应用价值,然而由于配对样本难以收集和人脸老化机制复杂等原因,目前研究较少。针对此情况,提出一种基于双重对偶生成对抗网络（double dual generative adversarial networks,D-DualGANs）的跨年龄素描-照片转换方法。方法 该网络通过设置4个生成器和4个判别器,以对抗训练的方式,分别学习素描到照片、源年龄组到目标年龄组的正向及反向映射。使素描图像与照片图像的生成过程相结合,老化图像与退龄图像的生成过程相结合,分别实现图像风格属性和年龄属性上的对偶。并增加重构身份损失和完全重构损失以约束图像生成。最终使输入的来自不同年龄组的素描图像和照片图像,分别转换成对方年龄组下的照片和素描。结果 为香港中文大学面部素描数据集（Chinese University of Hong Kong（CUHK）face sketch database,CUFS）和香港中文大学面部素描人脸识别技术数据集（CUHK face sketch face recognition technology database,CUFSF）的图像制作对应的年龄标签,并依据标签将图像分成3个年龄组,共训练6个D-DualGANs模型以实现3个年龄组图像之间的两两转换。同非端到端的方法相比,本文方法生成图像的变形和噪声更小,且年龄平均绝对误差（mean absolute error,MAE）更低,与原图像相似度的投票对比表明1130素描与3150照片的转换效果最好。结论 双重对偶生成对抗网络可以同时转换输入图像的年龄和风格属性,且生成的图像有效保留了原图像的身份特征,有效解决了图像跨风格且跨年龄的转换问题。     

State of the Art on Neural Rendering

Efficient rendering of photo-realistic virtual worlds is a long standing effort of computer graphics. Modern graphics techniques have succeeded in synthesizing photo-realistic images from hand-crafted scene representations. However, the automatic generation of shape, materials, lighting, and other aspects of scenes remains a challenging problem that, if solved, would make photo-realistic computer graphics more widely accessible. Concurrently, progress in computer vision and machine learning have given rise to a new approach to image synthesis and editing, namely deep generative models. Neural rendering is a new and rapidly emerging field that combines generative machine learning techniques with physical knowledge from computer graphics, e.g., by the integration of differentiable rendering into network training. With a plethora of applications in computer graphics and vision, neural rendering is poised to become a new area in the graphics community, yet no survey of this emerging field exists. This state-of-the-art report summarizes the recent trends and applications of neural rendering. We focus on approaches that combine classic computer graphics techniques with deep generative models to obtain controllable and photorealistic outputs. Starting with an overview of the underlying computer graphics and machine learning concepts, we discuss critical aspects of neural rendering approaches. Specifically, our emphasis is on the type of control, i.e., how the control is provided, which parts of the pipeline are learned, explicit vs. implicit control, generalization, and stochastic vs. deterministic synthesis. The second half of this state-of-the-art report is focused on the many important use cases for the described algorithms such as novel view synthesis, semantic photo manipulation, facial and body reenactment, relighting, free-viewpoint video, and the creation of photo-realistic avatars for virtual and augmented reality telepresence. Finally, we conclude with a discussion of the social implications of such technology and investigate open research problems.     

Real reality

In its most basic form, computer graphics technology renders an image of the world from a model. Having refined techniques from vector graphics, computer graphics now includes improved methods to render realistic and informative visual images of models representing microcosms of interest. Computational technology includes mechanisms to compress, communicate and combine text, audio, graphics and video to provide a unified multimedia document. Users can now decide if they want to read a story, watch a video or combine information from multiple sources to create a personalized digital experience. So what future faces computer graphics and multimedia? Can we take the technology to still another level of reality? Let's assume we can expand the scope of computer graphics to produce and render a world model for information or entertainment that surpasses the visual, also representing sound, touch, smell and taste. Although seemingly far out now, I believe computer graphics and multimedia will combine and expand to make such a technology-real reality-possible. Virtual reality (VR) foreshadows this development. I believe real reality, or what may more accurately be called remote reality, lies just around the corner. Real reality will revolutionize our society in many ways. Unlike VR, real reality systems will let users experience and interact digitally with real environments using all the human senses. However, real reality experiences will remain free of time and space constraints. You will be able to experience a remote environment digitally at your convenience wherever you are     

基于算子系统的渐进式图像建模方法*

提出了一个基于单幅或多幅未校准图像的渐进交互式三维建模方法及相应系统。该方法的主要特点在于,按照一般人的建模习惯,由粗到细地通过图像重建目标三维模型,在确定大致形状的基础上,由用户添加或者修改投影约束与空间约束,并施加拓扑修改,逐步实现照相机定标,粗糙模型的求精,并最终完成对具有任意几何及拓扑物体的重建。在交互过程中,实时地求解几何参数与照相机投影矩阵,并在一个三维窗口中显示重建结果。     

Dynamic Fractal Transform with Applications to Image Data Compression

A recent trend in computer graphics and image processing is to use Iterated Function System(IFS)to generate and describe both man-made graphics and natural images.Jacquin was the first to propose a fully automation gray scale image compression algorithm which is referred to as a typical static fractal transform based algorithm in this paper.By using this algorithm,an image can be condensely described as a fractal transform operator which is the combination of a set of reactal mappings.When the fractal transform operator is iteratedly applied to any initial image,a unique attractro(reconstructed image)can be achieved.In this paper,a dynamic fractal transform is presented which is a modification of the static transform.Instea of being fixed,the dynamic transform operator varies in each decoder iteration,thus differs from static transform operators.The new transform has advantages in improving coding efficiency and shows better convergence for the deocder.     

基于LBC的计算机生成图像盲鉴别算法

针对现有的计算机生成图像盲鉴别算法选用的分类特征维度较高、通用性差等问题,提出了一种基于局部二进制计数模式的计算机生成图像盲鉴别算法.首先,将原始图像由RGB颜色空间转换为HSV颜色空间;然后,提取HSV颜色空间图像及其下采样图像的局部二进制计数模式矩阵,求取矩阵归一化直方图;最后,将上述直方图作为分类特征送入SVM分类器,实现计算机生成图像的盲鉴别.实验结果表明,该算法可以有效地鉴别自然图像和计算机生成图像,与现有算法相比具有更高的识别率和较低的特征维度.     

Compressive Image Reconstruction in Reduced Union of Subspaces

We present a new compressed sensing framework for reconstruction of incomplete and possibly noisy images and their higher dimensional variants, e.g. animations and light‐fields. The algorithm relies on a learning‐based basis representation. We train an ensemble of intrinsically two‐dimensional (2D) dictionaries that operate locally on a set of 2D patches extracted from the input data. We show that one can convert the problem of 2D sparse signal recovery to an equivalent 1D form, enabling us to utilize a large family of sparse solvers. The proposed framework represents the input signals in a reduced union of subspaces model, while allowing sparsity in each subspace. Such a model leads to a much more sparse representation than widely used methods such as K‐SVD. To evaluate our method, we apply it to three different scenarios where the signal dimensionality varies from 2D (images) to 3D (animations) and 4D (light‐fields). We show that our method outperforms state‐of‐the‐art algorithms in computer graphics and image processing literature.