结合统计分类和边缘特征的最优视图提取

已有视图度量无法同时描述3维模型整体和局部细节特征,因此难以得到理想的最优视图.提出一种结合统计分类和视图边缘细节特征的最优视图提取算法.首先,采用Adaboost进行样例学习,通过最优视图之间的几何特征相似性得到候选视图集合.然后,定义边缘分布熵对候选视图进行局部特征分析,用以提取最优视图,从而使提取出来的最优视图能够有效描述出3维模型的结构特征和内在细节特征,符合人类视觉感知效果.最后,通过3维模型数据库对算法进行统计分析.实验结果表明,本文算法要优于类似的最优视图算法.     

基于特征线条的三维模型检索方法

为了避免在三维模型检索中对输入源的限制,提出一种以自然图像为输入源、基于特征线条的三维模型检索方法.首先基于最优视点提取算法训练并获取三维模型较优视点集;然后在较优视点集下渲染三维模型混合轮廓线视图,并为各视点混合轮廓线视图提取Gabor边缘响应特征,建立特征库;最后对输入的自然图像提取相同的边缘响应特征,采用视觉词袋方法从特征库中检索相似模型,并根据相似度排序.实验结果表明,该方法利用自然图像与模型特征线视图的边缘相似性实现三维模型检索,降低了退化视图与自然图像纹理对三维模型检索的干扰,符合人类视觉辨识三维物体的机理,具有良好的检索效果.     

基于深度卷积神经网络的三维模型检索

为了更有效地利用三维模型数据集进行特征的自主学习,提出一种使用自然图像作为输入源,以三维模型的较优视图集为基础,通过深度卷积神经网络的训练提取深度特征用于检索的三维模型检索方法。首先,从多个视点对三维模型进行视图提取,并根据灰度熵的排序选取较优视图;然后,通过深度卷积神经网络对视图集进行训练,从而提取较优视图的深度特征并进行降维,同时,对输入的自然图像提取边缘轮廓图,经过相似度匹配获得一组三维模型;最后,基于检索结果中同类模型总数占检索列表长度的比例对列表进行重排序,从而获得最终的检索结果。实验结果表明,该算法能够有效利用深度卷积神经网络对三维模型的视图进行深度特征提取,同时降低了输入源的获取难度,有效提高了检索效果。     

特征自适应的三维模型最优视点提取

针对目前采用不同几何特征度量的视点优化算法在普适性方面的局限性,提出一种与三维模型特征相适应的视点优化算法.首先提取三维模型混合特征,采用AdaBoost分类器对三维模型混合特征与相适应的视点计算算法进行匹配关系训练学习,构造最优视点分类器以提取最优视点,即将最优视点提取问题转化为分类问题;对于查询模型,通过训练后的最优视点分类器获得适应模型特征的视点优化算法,并计算模型的最优视点.实验结果表明:该算法有效反映三维模型的结构特征和细节,结果优于单一度量视点提取算法.     

基于形状分布的三维骨骼的相似性度量

文中应用形状分布算法度量由CT数据重建出的三维骨骼的相似度,并提出了改进.基本步骤是:在模型表面选择随机点,计算每两点间的距离,以形状分布函数来构建形状分布直方图,通过比较形状分布直方图来给出不同骨骼间的相似度.实验表明,该方法能够准确度量骨骼的相似性.     

环视图表示下的无监督三维物体检索

为了解决基于多视图的三维物体检索方法过度依赖基于人工标注的有监督训练的问题,提出了一种基于环视图的无监督三维物体检索算法.首先,训练面向多圈环视图的无监督深度网络模型,通过随机数据混合增强学习不同形状之间的内在联系;其次,基于最优匹配方法计算物体间的相似性,其中,最优匹配是利用2个物体环视图间最小距离的平均值计算得到;最后,利用环视图特征过滤算法去除冗余数据,能够在保持精度稳定的情况下,有效地减少相似性匹配的计算代价.在ModelNet40数据集和SHREC15数据集上进行实验,文中方法精度指标mAP分别为41.2％和54.5％.实验结果表明,该无监督三维物体检索方法取得了优异的性能,有效地降低了人工标注的成本.     

基于形状分布的三维骨骼的相似性度量

文中应用形状分布算法度量由CT数据重建出的三维骨骼的相似度,并提出了改进。基本步骤是:在模型表面选择随机点,计算每两点间的距离,以形状分布函数来构建形状分布直方图,通过比较形状分布直方图来给出不同骨骼间的相似度。实验表明,该方法能够准确度量骨骼的相似性。     

基于距离度量学习的集成谱聚类

无监督学习聚类算法的性能依赖于用户在输入数据集上指定的距离度量,该距离度量直接影响数据样本之间的相似性计算,因此,不同的距离度量往往对数据集的聚类结果具有重要的影响。针对谱聚类算法中距离度量的选取问题,提出一种基于边信息距离度量学习的谱聚类算法。该算法利用数据集本身蕴涵的边信息,即在数据集中抽样产生的若干数据样本之间是否具有相似性的信息,进行距离度量学习,将学习所得的距离度量准则应用于谱聚类算法的相似度计算函数,并据此构造相似度矩阵。通过在UCI标准数据集上的实验进行分析,结果表明,与标准谱聚类算法相比,该算法的预测精度得到明显提高。     

浮雕显著性信息熵驱动的三维模型最优视点选择

在三维模型最优视点选择中,将模型的浮雕显著性信息度量引入模型视点互信息的信息熵分析,提出一种结合视觉显著性的模型视见描述子刻画方法.针对模型视点球的各个视点计算模型可见面片浮雕显著性信息熵驱动的视见描述子,并从中选择视见描述子值最大的视点作为模型的最优观察视点.实验结果表明,由该方法获取的最优视点得到的视图能够反映和展示三维模型的视觉显著特征.     

基于粒子群算法的三维CAD模型相似性计算

为了更加准确地度量两个模型之间的形状差异,提出了一种基于粒子群的模型相似性计算方法。利用面的组成边数来构造面相似度矩阵,通过粒子群算法对该矩阵进行搜索,得到了两个模型之间的最优面匹配序列。根据这个最优面匹配序列,从面相似度矩阵中提取对应的面相似性值。通过累积面之间的相似性来计算模型之间的整体相似性。以此为基础来度量模型之间的差异。实验结果表明：该方法能够准确地度量两个模型之间的相似程度。     

Asymmetric and selective object rendering for optimized Cloud Mobile 3D Display Gaming user experience

Cloud Mobile 3D Display Gaming has been recently proposed where 3D video rendering and encoding are performed on cloud servers, with the resulting 3D video streamed wirelessly to mobile devices with 3D displays. This approach has the advantage of relieving high computation, power and storage requirements of 3D display gaming from mobile devices, while enabling game developers to focus on a single rich version of the game which can be experienced from any mobile device and platform. However, it is challenging to stream 3D video over dynamically fluctuating and often constrained mobile networks. In this paper, we propose a novel technique called Asymmetric and Selective Object Rendering (ASOR) which proves to be more powerful than previous solutions for Cloud based Mobile 3D display gaming. Specifically, this technique will enable rendering engine to intelligently decide whether or not to render an individual object and how good the corresponding texture detail will be if rendered, and the settings can be asymmetric for two views. Thus, unimportant objects can trade quality for reduced bitrate while important objects can remain high quality so that the overall user experience is optimized given certain bandwidth constraints. To quantitatively measure the user experience and bitrate by applying different rendering settings, we develop a user experience model and a bitrate model. We further propose an optimization algorithm which uses the above two models to automatically decide the optimal rendering settings for left view and right view to ensure the best user experience given the network conditions. Experiments conducted using real 4G-LTE network profiles on commercial cloud service with different genres of games demonstrate significant improvement in user experience when the proposed optimization algorithm is applied.     

基于深度学习的运动目标交接算法

针对多摄像机非重叠视域下存在的运动目标不连续性和不确定性的问题, 提出一种基于深度学习的运动行人目标的交接算法. 首先基于深度卷积神经网络构建人脸特征提取模型, 对人脸特征提取模型进行训练, 获得精确的人脸特征. 然后比较两种常用的相似度度量方法, 选择其中一种更适合的相似度度量方法, 以完成最优的人脸匹配过程, 提高人脸匹配的准确率. 最后通过对不同摄像机下的人脸进行特征匹配找到最匹配的人脸, 实现运动目标的交接. 实验表明, 深度神经网络可以减少运动目标丢失的概率, 准确地提取到运动目标的人脸特征, 有效完成多摄像机下运动目标的交接跟踪任务.     

Online Personalised Non‐photorealistic Rendering Technique for 3D Geometry from Incremental Sketching

This paper presents an online personalised non‐photorealistic rendering (NPR) technique for 3D models generated from interactively sketched input. This technique has been integrated into a sketch‐based modelling system. It lets users interact with computers by drawing naturally, without specifying the number, order, or direction of strokes. After sketches are interpreted as 3D objects, they can be rendered with personalised drawing styles so that the reconstructed 3D model can be presented in a sketchy style similar in appearance to what have been drawn for the 3D model. This technique captures the user's drawing style without using template or prior knowledge of the sketching style. The personalised rendering style can be applied to both visible and initially invisible geometry. The rendering strokes are intelligently selected from the input sketches and mapped to edges of the 3D object. In addition, non‐geometric information such as surface textures can be added to the recognised object in different sketching modes. This will integrate sketch‐based incremental 3D modelling and NPR into conceptual design.     

基于HMM的单样本可变光照、姿态人脸识别

提出了一种基于HMM的单样本可变光照、姿态人脸识别算法.该算法首先利用人工配准的训练集对单张正面人脸输入图像与Candide3模型进行自动配准,在配准的基础上重建特定人脸三维模型.对重建模型进行各种角度的旋转可得到姿态不同的数字人脸,然后利用球面谐波基图像调整数字人脸的光照系数可产生光照不同的数字人脸.将产生的光照、姿态不同的数字人脸同原始样本图像一起作为训练数据,为每个用户建立其独立的人脸隐马尔可夫模型.将所提算法对现有人脸库进行识别,并与基于光照补偿和姿态校正的识别方法进行比较.结果显示,该算法能有效避免光照补偿、姿态校正方法因对某些光照、姿态校正不理想而造成的识别率低的情况,能更好地适应光照、姿态不同条件下的人脸识别.     

ClipFlip : Multi‐view Clipart Design

We present an assistive system for clipart design by providing visual scaffolds from the unseen viewpoints. Inspired by the artists' creation process, our system constructs the visual scaffold by first synthesizing the reference 3D shape of the input clipart and rendering it from the desired viewpoint. The critical challenge of constructing this visual scaffold is to generate a reference 3D shape that matches the user's expectations in terms of object sizing and positioning while preserving the geometric style of the input clipart. To address this challenge, we propose a user‐assisted curve extrusion method to obtain the reference 3D shape. We render the synthesized reference 3D shape with a consistent style into the visual scaffold. By following the generated visual scaffold, the users can efficiently design clipart with their desired viewpoints. The user study conducted by an intuitive user interface and our generated visual scaffold suggests that our system is especially useful for estimating the ratio and scale between object parts and can save on average 57% of drawing time.     

面向2D对象形状识别的空间模糊查询研究

基于空间形状的查询与认知主体的空间推理密切相关。从空间认知的角度,通常希望查询结果是一类形状结构相似的对象集合。以形状的不确定性表达和模糊查询为研究内容,提出一种面向2D对象形状识别的空间查询方法--向心包络算法。算法将对象划分为以最大内径中心为公共点的三角形集合,在此基础上建立相应的形状度量方法,通过提取所有顶点关于对象整体结构的形状影响因子求得对象之间的形状相似度,并建立与模糊形状谓词的匹配关系。实验表明,该方法可以实现2D对象的空间模糊查询,且查询结果与模糊形状谓词基本一致。     

Depth image‐based rendering for multiview generation

Abstract— Techniques for 3‐D display have evolved from stereoscopic 3‐D systems to multiview 3‐D systems, which provide images corresponding to different viewpoints. Currently, new technology is required for application in multiview display systems that use input‐source formats such as 2‐D images to generate virtual‐view images of multiple viewpoints. Due to the changes in viewpoints, occlusion regions of the original image become disoccluded, resulting in problems related to the restoration of output image information that is not contained in the input image. In this paper, a method for generating multiview images through a two‐step process is proposed: (1) depth‐map refinement and (2) disoccluded‐area estimation and restoration. The first step, depth‐map processing, removes depth‐map noise, compensates for mismatches between RGB and depth, and preserves the boundaries and object shapes. The second step, disoccluded‐area estimation and restoration, predicts the disoccluded area by using disparity and restores information about the area by using information about neighboring frames that are most similar to the occlusion area. Finally, multiview rendering generates virtual‐view images by using a directional rendering algorithm with boundary blending.     

Shape-aware Volume Illustration

We introduce a novel volume illustration technique for regularly sampled volume datasets. The fundamental difference between previous volume illustration algorithms and ours is that our results are shape-aware, as they depend not only on the rendering styles, but also the shape styles. We propose a new data structure that is derived from the input volume and consists of a distance volume and a segmentation volume. The distance volume is used to reconstruct a continuous field around the object boundary, facilitating smooth illustrations of boundaries and silhouettes. The segmentation volume allows us to abstract or remove distracting details and noise, and apply different rendering styles to different objects and components. We also demonstrate how to modify the shape of illustrated objects using a new 2D curve analogy technique. This provides an interactive method for learning shape variations from 2D hand-painted illustrations by drawing several lines. Our experiments on several volume datasets demonstrate that the proposed approach can achieve visually appealing and shape-aware illustrations. The feedback from medical illustrators is quite encouraging.