基于图像的实时漫游

提出了一个点和多边形模型混合的场影表达方式，从而实现了对复杂场景的视点不受限制的实时漫游。它从多幅带深度的参考图像出发，在预处理阶段区别对待场景中平面物体和曲面物体在参考图像中的对应像素。对于在参考图像所占区域较大的空间平面，用传统的多边形模型方式对其进行表达，试图恢复出其平面方程，然后通过采样密度比较和重采样过程，将该空间平面在所有参考图像中的出现合并成一个均匀采样的纹理图像；而对于空间曲面或在参考图像中所占面积较小的平面，使用点的形式对其进行表达，通过采样密度的比较去掉冗余的点，将保留下来的点按其空间位置进行聚类。同时，对于场景中那些不被所有参考图像所拍摄到而在漫游过程中可能形成空洞的部分，提出一个空洞预填补技术，在预处理阶段即对这类空洞进行填补，从而大大较少了漫游阶段出现空洞的几度。在漫游阶段则使用纹理映射和点Warping的方式进行绘制，以充分利用图形硬件的加速功能。     

基于块的任意曲面上的纹理合成

一种新的曲面纹理合成技术被提出,它采用求最小割集来解决块拼接时的礁缝走样问题。算法在预处理期对模型的三维网格进行了重建,使其规则并且建立网格点与参数化栅格采样后的图像点一一对应的关系,无论对合成的速度和质量都有很大的提高。提出了在曲面上进行纹理粘贴的算法,对于渲染存在不完整性的自然物体取得了较好的效果。     

基于平面的Warping技术

提出了一种基于平面的逆向Warping算法,用于根据多幅参考图像生成任意视点下的新图像.首先通过参考图像的深度信息来重建三维平面,然后寻找这些重建平面间的对应关系,并比较它们对空间平面同一部分的采样密度,以获得最好的采样结果.在生成新视点图像时,首先对那些采样密度最好的重建平面进行可见性判断,然后将其投影到新视点下,在此基础上求得目标图像上各点的深度,最后将目标图像上的点逆向Warping到相应的参考图像中,以获取它们的颜色值.同时,对于参考图像中不能被重建成平面的像素点,用正向Warping的方法对其进     

条纹理映射

提出一种新的基于图像绘制的方法，能高效地利用图形硬件进行加速，避免成像过程中烦人的空洞填补计算,高质量地反映物体表面的三雏凹凸细节及视差变化．该方法首先为源深度图像中每个像素生成一个条状的纹理(条纹理)，即根据一个像素及其邻近像素的深度值，沿着深度方向为该像素插值生成多个具有不同深度值的点，它们一起构成谊像素的条纹理；然后，绘制时利用图形硬件的纹理映射直接处理这些条纹理.由于各个像素的条纹理的集合可以构成源场景的近似连续三维表示,从而大大增强了源深度图像表达三维模型细节的能力，而且成像时不必进行空洞填补的计算.与已有的同类方法相比，新方法的空间需求小，成像速度快，并且成像质量很高．     

从多幅参考图像合成目标图像的逆映射算法

提出了一种从多幅参考图像来合成新视点目标图像的逆映射算法.这种方法不但成功地填补了由于投影区域扩张而产生的第1类空洞,而且还成功地填补了由于空间非深度连续物体相互遮挡而产生的第2类空洞,从而方便地实现了虚拟环境中的漫游.基于物体表面深度的连续性,提出了一种位移预测方法.该方法可以从单幅参考图像获得逆映射过程中所需要的目标图像的位移信息,从而大大提高了算法的效率.与通常的正向映射算法相比,该算法克服了多幅参考图像所带来的计算量成倍增长等问题,而且误差较小.     

点模型的几何图像简化法

提出一种基于几何图像的曲率自适应点模型简化算法.首先将点模型的球面极坐标映射到平面上,构造其几何图像;然后利用几何图像确定点模型中点的k-最近邻域及其曲面变分;最后结合曲面变分和简化密度对点集曲面重采样,并通过移动最小二乘曲面评估简化的误差.实验结果表明,该算法执行速度快、易于控制采样密度和保持曲面细节,且能够生成高质量的简化曲面.     

虚平面映射:深度图像内部视点的绘制技术

首先推导与归纳了图像三维变换中像素深度场的变换规律,同时提出了基于深度场和极线原则的像素可见性别方法,根据上述理论和方法,提出一种基于深度图像的建模与绘制(image-based modeling and rendering,简称IBMR)技术,称为虚平面映射.该技术可以基于图像空间内任意视点对场景进行绘制.绘制时,先在场景中根据视线建立若干虚拟平面,将源深度图像中的像素转换到虚平面上,然后通过对虚平面上像素的中间变换,将虚平面转换成平面纹理,再利用虚平面的相互拼接,将视点的成像以平面纹理映射的方式完成.新方法还能在深度图像内侧,基于当前视点快速获得该视点的全景图,从而实现视点的实时漫游.新方法视点运动空间大、存储需求小,且可以发挥图形硬件的纹理映射功能,并能表现物体表面的三维凹凸细节和成像视差效果,克服了此前类似算法的局限和不足.     

一种基于多边形柱面全景图的虚拟漫游新方法

提出了一种基于图像绘制的多边形柱面全景图的虚拟漫游方法。利用普通 的手持相机在一个多边形区域内沿某一路径拍摄并拼接多幅全景图,通过基于SIFT 的特征 点检测来计算深度,用狭缝图像插值来实现整个区域内的平滑漫游。该方法具有采样简单、 虚拟场景真实感强,支持连续大范围漫游的特点。     

基于光场的渲染技术研究

基于图像的渲染技术(Image-Based Rendering,IBR)逐渐成为场景渲染的主要手段之一,目前已有大量的基于此技术的方法提出,其中光场渲染(Light Field Renderin,LFR)是在不需要图像的深度信息或相关性的条件下,通过相机阵列或由一个相机按设计好的路径移动把场景拍摄下来作为输入图像集,对于任意给定的新视点,找出该视点邻近的几个采样点进行简单的重新采样,就能得到该视点处的视图.本文采用两平面参数化的方法设计实施了一套光场渲染的软件方案,用光场渲染的方法实现了真实场景中物体的实时漫游.     

多视点成像的多边形模板法

该文提出一种对场景进行多视点成像的方法。该方法首先为场景中的多边形生成多边形模板，一个多边形模板，包括一条轮廓路径和一组纹条，而一个纹条是平行成像画的一个平面与多边形相交的直线段。由于纹条相对于不同视点的透视投影的变化是线性的，因此，绘制多边形时可以基于模板逐个纹条地处理，而不必按照传统的扫描转换方法逐个点地处理，绘制速度可以提高很多。同时，与视点无关的光照和纹理可以预先计算并保存在模板中，以便在成像时利用基于图像绘制的技术来生成高质量的图像。该方法中，视点可以放置在三维空间的任意位置，并且在场景漫游时可以根据视点位置自动地实现多分辨率绘制。     

Lumiproxy: A Hybrid Representation of Image-Based Models

In this paper,we present a hybrid representation of image-based models combining the textured planes and the hierarchical points.Taking a set of depth images as input,our method starts from classifying input pixels into two categories,indicating the planar and non-planar surfaces respectively.For the planar surfaces,the geometric coefficients are reconstructed to form the uniformly sampled textures.For nearly planar surfaces,some textured planes,called lumiproxies, are constructed to represent the equiva...     

基于稀疏点云的多平面场景稠密重建

多平面场景是生活中常见的一种场景,然而由于该类场景中常常存在物体表面纹理缺乏和纹理重复的现象,导致从多视图像重建获得的三维点云数据中存在点云过于稀疏甚至孔洞等问题,进而导致以微面片拟合三维点云所得到的重建表面出现平面颠簸现象.针对这些问题,本文提出了一种基于稀疏点云的分段平面场景重建方法.首先,利用分层抽样代替随机抽样,改进了J-Linkage多模型估计算法;然后,利用该方法对稀疏点云进行多平面拟合,来获得场景的多平面模型;最后,将多平面模型和无监督的图像分割相结合,提取并重建场景中的平面区域.场景中的非平面部分用CMVS/PMVS(Clustering views for multi-view stereo/patch-based multi-view stereo)算法重建.多平面模型估计的实验表明,改进的J-Linkage算法提高了模型估计的准确度.三维重建的实验证实,提出的重建方法在有效地克服孔洞和平面颠簸问题的同时,还能重建出完整平面区域.     

混合漫游系统

提出一种新颖的场景绘制方法,首先对图像进行处理,用交互的方法区分场景的背景和前景;然后分别建立背景和前景的3D几何模型,采用一种分片绘制的策略,进一步提高了绘制质量．通过将动态网格叠加到几何模型中,在静态图像中产生动态纹理,丰富场景内容,从而建立了一种混合场景表示,实现逼真的场景实时漫游．实验证明,该算法具有较好的普适性,可以处理包含灭点或灭线的不同类型照片、绘画和全景图．     

A novel plane extraction approach using supervised learning

This paper presents a novel approach for the classification of planar surfaces in an unorganized point clouds. A feature-based planner surface detection method is proposed which classifies a point cloud data into planar and non-planar points by learning a classification model from an example set of planes. The algorithm performs segmentation of the scene by applying a graph partitioning approach with improved representation of association among graph nodes. The planarity estimation of the points in a scene segment is then achieved by classifying input points as planar points which satisfy planarity constraint imposed by the learned model. The resultant planes have potential application in solving simultaneous localization and mapping problem for navigation of an unmanned-air vehicle. The proposed method is validated on real and synthetic scenes. The real data consist of five datasets recorded by capturing three-dimensional(3D) point clouds when a RGBD camera is moved in five different indoor scenes. A set of synthetic 3D scenes are constructed containing planar and non-planar structures. The synthetic data are contaminated with Gaussian and random structure noise. The results of the empirical evaluation on both the real and the simulated data suggest that the method provides a generalized solution for plane detection even in the presence of the noise and non-planar objects in the scene. Furthermore, a comparative study has been performed between multiple plane extraction methods.     

Patch-based variational image approximation

Vector graphic gives us a new solution to the representation of raster images. Among many types of vectorized representations, the most popular is mesh representation, which inherits the benefits of vector graphics. Inspired by mesh, we propose a novel patch-based representation for raster images, in which pixels are partitioned into regions, and pixels belonging to the same region are converted into a 3D point cloud and approximated by a 3D planar patch with proper boundaries in a variational way. The resulting patches are then encoded via a half-edge structure for storage. The key point is that the vertices of boundaries are not located on the very positions of sample points, i.e. converted pixels, but dependent on the optimal position of the patch, which theoretically reduces the fitting errors. Experiments show that our algorithm produces better results.     

基于Contourlet变换和均值漂移的SAR图像分割

基于斑噪特性和纹理特征，提出了一种完全无监督的SAR图像分割算法。针对SAR图像的Contourlet变换，提出了子带选取的能量标准，对选定的子带计算能量特征和共生特征；依据特征向量的相似度剔除相近特征向量，用均值漂移算法获取纹理区域数和相应的中心特征，用像素的特征向量与相应中心特征向量的距离确定它们的分类。该文提出的方法不需要先验知识和训练样本。实验表明，基于Contourlet变换的均值漂移分割算法对混合Brodatz图像和SAR图像的分割取得了满意结果。     

辐射度场景中双向纹理函数表面的绘制

双向纹理函数(BTF)表面一般采用点采样数据来定义表面的光照属性,因而这类表面很难运用基于面片分割的辐射度方法进行绘制,提出一种将辐射度算法扩展到包括BTF表面场景的有效方法.对表面的BTF样本区域首先进行像素聚类,再在各个像素类内对视线采样方向做进一步自适应的聚类,在各个视线类内像素分别拟合一个低频光照甬数,并求它们在各个视线类内光照细节的高频光照函数.低频光照函数作为该表面区域的平均反射属性参与辐射度计算,生成场景的整体光照效果;然后利用计算的辐射度值和高频光照函数重建该表面区域的BTF材质细节.文中方法不仅取得了较高的压缩效率,而且在BTF材质表面产生了辉映等全局光照效果.最后利用硬件实现了视点快速改变时的场景绘制.     

Accelerated Backward Warping

In this paper a plane-based backward warping algorithm is proposed to generate novel viwews from multiple reference images.First.depth information is employed to reconstruct space planes from individual refernce images and calculate the potential occluding relationship between these planes.Then the planes which represent each identical space plane from different reference images are compared with each other to decide the one with the best sample rate to be preserved and used in the later warping period while the other samples are abandoned.While the image of a novel view is produced,traditional methods in computer graphics,such as visibility test.and clipping,are used to process the planes reconstructed.Then the planes processed are projected onto the desired image form the knowledge on which plane the desired image pixels are warped from can be acquired.Finally,pixels‘ depth of the desired image is calculated and then a ackwared warping is performed from these pixels to the reference images to obtain their colors.The storage requirement in the algorithm is small and increases slowly with the number of reference images increases.By combining the strategy of only preserving the best sample parts and the backward warping algorithm ,the sample problem could be well tackled.     

Extracting objects from range and radiance images

In this paper, we present a pipeline and several key techniques necessary for editing a real scene captured with both cameras and laser range scanners. We develop automatic algorithms to segment the geometry from range images into distinct surfaces, register texture from radiance images with the geometry, and synthesize compact high-quality texture maps. The result is an object-level representation of the scene which can be rendered with modifications to structure via traditional rendering methods. The segmentation algorithm for geometry operates directly on the point cloud from multiple registered 3D range images instead of a reconstructed mesh. It is a top-down algorithm which recursively partitions a point set into two subsets using a pairwise similarity measure. The result is a binary tree with individual surfaces as leaves. Our image registration technique performs a very efficient search to automatically find the camera poses for arbitrary position and orientation relative to the geometry. Thus, we can take photographs from any location without precalibration between the scanner and the camera. The algorithms have been applied to large-scale real data. We demonstrate our ability to edit a captured scene by moving, inserting, and deleting objects     

Stereo using monocular cues within the tensor voting framework

We address the fundamental problem of matching in two static images. The remaining challenges are related to occlusion and lack of texture. Our approach addresses these difficulties within a perceptual organization framework, considering both binocular and monocular cues. Initially, matching candidates for all pixels are generated by a combination of matching techniques. The matching candidates are then embedded in disparity space, where perceptual organization takes place in 3D neighborhoods and, thus, does not suffer from problems associated with scanline or image neighborhoods. The assumption is that correct matches produce salient, coherent surfaces, while wrong ones do not. Matching candidates that are consistent with the surfaces are kept and grouped into smooth layers. Thus, we achieve surface segmentation based on geometric and not photometric properties. Surface overextensions, which are due to occlusion, can be corrected by removing matches whose projections are not consistent in color with their neighbors of the same surface in both images. Finally, the projections of the refined surfaces on both images are used to obtain disparity hypotheses for unmatched pixels. The final disparities are selected after a second tensor voting stage, during which information is propagated from more reliable pixels to less reliable ones. We present results on widely used benchmark stereo pairs.