一种交互式图像去雾方法

在二色大气散射模型的基础上,根据雾对景物退化与景物深度的指数关系,采用交互方式,通过附加一些主观判断作为先验信息,从单幅图像中估计出景物深度,进行对比度增强,有效实现了彩色图像去雾。同时针对浓雾退化图像处理结果较暗的情况,进行了正态截取拉伸,提高了图像亮度,获得了较好的视觉效果。     

基于深度学习的单幅图像超分辨率重建综述

单幅图像超分辨率SISR重建指从单幅低分辨率图像恢复出高分辨率图像.深度学习方法越来越多地用于图像超分辨重建领域,由于深度网络模型可以自主学习低分辨率图像到高分辨率图像之间的映射关系,与传统方法相比在该领域展现出了更好的重建效果,因而基于深度学习的方法已经成为目前图像超分辨率重建领域的主流方向.围绕现有的超分辨深度网络...     

基于监督学习的单幅图像深度估计综述

单幅图像深度估计是三维重建中基于图像获取场景深度的重要技术,也是计算机视觉中的经典问题,近年来,基于监督学习的单幅图像深度估计发展迅速.文中介绍了基于监督学习的单幅图像深度估计及其模型和优化方法;分析了现有的参数学习、非参数学习、深度学习3类方法及每类方法的国内外研究现状及优缺点;最后对基于监督学习的单幅图像深度估计进行总结,得出了深度学习框架下的单幅图像深度估计是未来研究的发展趋势和重点.     

一种平面物体射影不变性识别方法

提出一种基于方向可变滤波器的平面物体射影不变性识别方法。该方法首先利用方向可变滤波器检测出平面物体的边缘方向特征,从单幅图像中提取平面物体在射影变化下的不变特征,建立经典框架,然后用填充经典框架图像的矩识别物体。该方法是图像局部识别方法,允许景物中有部分的遮挡物存在。     

基于景物散焦图像的距离测量

计算机视觉中,景物三维重建的关键是从景物的图像中计算出景物目标到摄像机的距离,提出了一种基于散焦图像计算景物距离的新方法。该方法利用远心光学镜头拍摄景物图像,通过改变像检测到镜头的距离获得同一景物的两幅散焦程度不同的图像,将获得灰度图像转换成梯度图像。利用矩不变原理计算梯度图像中边缘区的大小与整个图像匹配大小的比Pe,根据两幅图像的Pe值计算出景物的深度。实验结果表明了该方法的有效性,并对该方法产生的误差进行了分析。     

基于非参数化采样的单幅图像深度估计

针对传统单幅图像深度估计线索不足及深度估计精度不准的问题,提出一种基于非参数化采样的单幅图像深度估计方法。该方法利用非参数化的学习手段,将现有RGBD数据集中的深度信息迁移到输入图像中去。首先计算输入图像和现有RGBD数据集多尺度的高层次图像特征;然后,在现有RGBD数据集中,基于高层次的图像特征通过kNN最近邻搜索找到若干与输入图像特征最匹配的候选图像,并将这些候选图像对通过SIFT流形变到输入图像进行对齐。最后,对候选深度图进行插值和平滑等优化操作便可以得到最后的深度图。实验结果表明,与现有算法相比,该方法估计得到的深度图精度更高,对输入图像的整体结构保持得更好。     

显微光学模糊图像的景物深度提取及应用

目的显微光学成像有景深小和易模糊等缺陷,很难根据几何光学中的点扩散函数准确评估图像的模糊程度,进而很难计算景物深度。同时,传统的使用边缘检测算子衡量图像模糊程度变化的方法缺少与景物深度之间的函数关系,影响深度计算的精度。为此,本文提出一种显微光学系统成像模糊程度与景物深度关系曲线的获取方法。方法从显微光学系统中的光学传递特性出发,建立光学传递函数中的光程差、高频能量参数和景物深度之间的数学关系,并通过归一化和曲线拟合得到显微光学系统的成像模糊程度与景物深度之间的解析函数。结果为了验证本文获取的图像模糊程度和景物深度之间的函数关系,首先使用纳米方形栅格的模糊图像进行深度计算,实验测得的深度平均误差为0.008μm,即相对误差为0.8%,与通过清晰图像和模糊图像的逐个像素亮度值比较,根据最小二乘方法搜索两幅图像的亮度差最小时求得深度的方法相比,精度提高了约73%。然后基于深度测量结果进行模糊栅格图像的清晰重构,重构后的图像在平均梯度和拉普拉斯值两个方面都明显提高,且相对于传统基于高斯点扩散函数清晰重构方法,本文方法的重构精度更高,稳定性更强;最后通过多种不同形状和亮度特性的栅格模糊图像的深...     

基于单幅图像的三维浏览图生成算法

传统的建模方式非常复杂,而日常生活中拍摄的多数照片本身包含着足够几何信息,于是文中提出了从单幅图像中直接生成具有三维动态效果的系列图片的设想。首先需要用户简化勾画出图像的遮挡关系,然后将图像按遮挡关系进行分层,针对每一个图层,根据提取出的特征边缘来识别出有意义的空间信息,最后从新的视角出发,重定景物间的关系和相对位置,进而生成具有三维浏览效果的图像。实验结果表明,该方法在用户简单参与下能得到良好效果。     

基于单幅图像的三维浏览图生成算法

传统的建模方式非常复杂,而日常生活中拍摄的多数照片本身包含着足够几何信息,于是文中提出了从单幅图像中直接生成具有三维动态效果的系列图片的设想。首先需要用户简化勾画出图像的遮挡关系,然后将图像按遮挡关系进行分层,针对每一个图层,根据提取出的特征边缘来识别出有意义的空间信息,最后从新的视角出发,重定景物间的关系和相对位置,进而生成具有三维浏览效果的图像。实验结果表明,该方法在用户简单参与下能得到良好效果。     

多尺度密集时序卷积网络的单幅图像去雨方法

雨滴会降低户外拍摄图像质量,影响图像视觉效果及后续图像分析工作。针对目前去雨算法存在颜色失真、去雨过度化等问题,为了提高计算机视觉算法在中、大雨天气下的准确性,提出多尺度DenseTimeNet(密集时间序列卷积神经网络)的单幅图像去雨方法。该网络由多个尺度DenseTimeNetBlock(密集时序卷积网络密集块)组成,通过卷积下采样技术得到不同尺度下雨线特征信息与降低图像维度后利用时域卷积寻找的时间维度特征信息。在不同维度下学习雨景图和无雨图之间的映射关系,网络主体由密集卷积块和残差网络组成,可加速算法收敛速度,更深度学习图像纹理特征,使特征信息在网络结构进行深度传播,可以更好地复原残损图像。在不同方向,不同大小的雨滴图像上对所提方法进行验证,实验结果表明,该方法相较于现有算法,图像去雨效果良好。     

一种基于图像区域系综分类的室外场景理解方法

多层感知机分类器是一种有效的数据分类方法，但其分类性能受训练样本空间的限制。通过多层感知机分类器系综提高室外场景理解中图像区域的分类性能，提出了一种自动识别室外场景图像中多种景物所属概念类别的方法。该方法首先提取图像分割区域的低层视觉特征，然后基于系综分类方法建立区域视觉特征和语义类别的对应关系，通过合并相同标注区域，确定图像中景物的高层语义。对包含5种景物的150幅图像进行测试，识别率达到了87％。与基于多层感知机方法的实验结果相比，本文提出的方法取得了更好的性能，这表明该方法适合于图像区域分类。此外，系综方法还可以推广到其他的分类问题。     

多特征组合的深度图像分割算法

深度图像直接反映景物表面的三维几何信息,且不受光照、阴影等因素的影响,对深度图像处理、识别、理解是目前计算机视觉领域研究的热点和重点之一。针对深度图像信息单一且噪声较大的特点,提出一种基于组合特征的阈值分割算法,实现对深度图像数据的有效分割。算法首先通过梯度特征对图像进行Otsu阈值分割;在此基础上,分别在不同分割区域内利用深度特征进行Otsu多阈值分割,得到候选目标;然后,在空域上利用像素的位置特征对候选目标进行分割、合并与去噪,最终得到图像分割的结果。实验结果表明,该方法能有效克服深度图像中噪声的影响,得到的分割区域边界准确,分割质量较高,为以后的室内对象识别和场景理解工作奠定了较好的基础。     

Removal of partial occlusion from single images

This paper examines large partial occlusions in an image which occur near depth discontinuities when the foreground object is severely out of focus. We model these partial occlusions using matting, with the alpha value determined by the convolution of the blur kernel with a pinhole projection of the occluder. The main contribution is a method for removing the image contribution of the foreground occluder in regions of partial occlusion, which improves the visibility of the background scene. The method consists of three steps. First, the region of complete occlusion is estimated using a curve evolution method. Second, the alpha value at each pixel in the partly occluded region is estimated. Third, the intensity contribution of the foreground occluder is removed in regions of partial occlusion. Experiments demonstrate the method's ability to remove the effects of partial occlusion in single images with minimal user input.     

Hallucinating Stereoscopy from a Single Image

We introduce a novel method for enabling stereoscopic viewing of a scene from a single pre‐segmented image. Rather than attempting full 3D reconstruction or accurate depth map recovery, we hallucinate a rough approximation of the scene's 3D model using a number of simple depth and occlusion cues and shape priors. We begin by depth‐sorting the segments, each of which is assumed to represent a separate object in the scene, resulting in a collection of depth layers. The shapes and textures of the partially occluded segments are then completed using symmetry and convexity priors. Next, each completed segment is converted to a union of generalized cylinders yielding a rough 3D model for each object. Finally, the object depths are refined using an iterative ground fitting process. The hallucinated 3D model of the scene may then be used to generate a stereoscopic image pair, or to produce images from novel viewpoints within a small neighborhood of the original view. Despite the simplicity of our approach, we show that it compares favorably with state‐of‐the‐art depth ordering methods. A user study was conducted showing that our method produces more convincing stereoscopic images than existing semi‐interactive and automatic single image depth recovery methods.     

Semantic image segmentation using low-level features and contextual cues

Semantic image segmentation aims to partition an image into non-overlapping regions and assign a pre-defined object class label to each region. In this paper, a semantic method combining low-level features and high-level contextual cues is proposed to segment natural scene images. The proposed method first takes the gist representation of an image as its global feature. The image is then over-segmented into many super-pixels and histogram representations of these super-pixels are used as local features. In addition, co-occurrence and spatial layout relations among object classes are exploited as contextual cues. Finally the features and cues are integrated into the inference framework based on conditional random field by defining specific potential terms and introducing weighting functions. The proposed method has been compared with state-of-the-art methods on the MSRC database, and the experimental results show its effectiveness.     

Object Repositioning Based on the Perspective in a Single Image

We propose an image editing system for repositioning objects in a single image based on the perspective of the scene. In our system, an input image is transformed into a layer structure that is composed of object layers and a background layer, and then the scene depth is computed from the ground region that is specified by the user using a simple boundary line. The object size and order of overlapping are automatically determined during the reposition based on the scene depth. In addition, our system enables the user to move shadows along with objects naturally by extracting the shadow mattes using only a few user‐specified scribbles. Finally, we demonstrate the versatility of our system through applications to depth‐of‐field effects, fog synthesis and 3D walkthrough in an image.     

Depth from focus using a pyramid architecture

A method is presented for depth recovery through the analysis of scene sharpness across changing focus position. Modeling a defocused image as the application of a low pass filter on a properly focused image of the same scene, we can compare the high spatial frequency content of regions in each image and determine the correct focus position. Recovering depth in this manner is inherently a local operation, and can be done efficiently using a pipelined image processor. Laplacian and Gaussian pyramids are used to calculate sharpness maps which are collected and compared to find the focus position that maximizes high spatial frequencies for each region.     

基于前馈上下文和形状先验的平面标注方法

针对真实场景中由于互相遮挡导致的场景语义不能完全被理解的问题,提出了一种基于前馈上下文和形状先验的方法来对前景区域和被遮挡的背景区域进行语义标注。首先,将原始图像分割成超像素并提取像素点特征,采用加速决策树方法标注前景,同时采用改进的基于多尺度可形变的部件模型方法进行目标检测。其次,将可见对象信息与前馈上下文预测相结合来推测背景区域的被遮挡部分。然后,根据与当前标签置信度相匹配的多边形为每个标签提供形状先验知识。最后,结合像素预测与可视平面预测和多边形知识,以形成完整的场景标注图像。与现有方法相比,该方法能够得到与街道场景更相符的结果,并在人行道和公路较接近时的标注效果更好。     

Elimination of artifacts due to occlusion and discretization problems in image space blurring techniques

Traditional computer graphics methods render images that appear sharp at all depths. Adding blur can add realism to a scene, provide a sense of scale, and draw a viewer’s attention to a particular region of a scene. Our image-based blur algorithm needs to distinguish whether a portion of an image is either from a single object or is part of more than one object. This motivates two approaches to identify objects after an image has been rendered. We illustrate how these techniques can be used in conjunction with our image space method to add blur to a scene.