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.     

A high-quality 3D multiview model-building technique based on CAD

In this paper, we propose a method for building a high-quality 3D model efficiently from a CAD model. We automatically build the high-quality 3D model of an object by accurately extracting the 3D multiview features from the CAD model with the object-precision method instead of the existing image-precision method. Precision of the features from the image-precision method is limited to the precision of the image resolution and varies with the view distance and view-up vector. Since we exploit the object-precision method to extract the 3D multiview features, the precision of the features is equal to the precision at which the object is defined in the CAD and is independent of the view distance and view-up vector.     

Automatic facial feature extraction and 3D face modeling using two orthogonal views with application to 3D face recognition

We present a fully automated algorithm for facial feature extraction and 3D face modeling from a pair of orthogonal frontal and profile view images of a person's face taken by calibrated cameras. The algorithm starts by automatically extracting corresponding 2D landmark facial features from both view images, then compute their 3D coordinates. Further, we estimate the coordinates of the features that are hidden in the profile view based on the visible features extracted in the two orthogonal face images. The 3D coordinates of the selected feature points obtained from the images are used first to align, then to locally deform the corresponding facial vertices of the generic 3D model. Preliminary experiments to assess the applicability of the resulted models for face recognition show encouraging results.     

3D Shape Matching and Inspection Using Geometric Features and Relational Learning

In this paper we consider the problem of matching 3D sensed data with models and inspection for defects where the correspondence between models and data needs to be solved in robust and efficient ways. We explore the use of machine learning (in particular, relational learning) as an efficient method for solving correspondence (and so, pose estimation) as well as automatically generating rules for acceptable shape variations from training data. As an additional but necessary issue, we also consider the use of view-independent covariance methods for the extraction of surface features used to determine shape signatures which correspond to curvature-like surface attributes. Such features are utilized in the relational learning model.     

Coarse‐to‐Fine Isometric Shape Correspondence by Tracking Symmetric Flips

We address the symmetric flip problem that is inherent to multi‐resolution isometric shape matching algorithms. To this effect, we extend our previous work which handles the dense isometric correspondence problem in the original 3D Euclidean space via coarse‐to‐fine combinatorial matching. The key idea is based on keeping track of all optimal solutions, which may be more than one due to symmetry especially at coarse levels, throughout denser levels of the shape matching process. We compare the resulting dense correspondence algorithm with state‐of‐the‐art techniques over several 3D shape benchmark datasets. The experiments show that our method, which is fast and scalable, is performance‐wise better than or on a par with the best performant algorithms existing in the literature for isometric (or nearly isometric) shape correspondence. Our key idea of tracking symmetric flips can be considered as a meta‐approach that can be applied to other multi‐resolution shape matching algorithms, as we also demonstrate by experiments.     

基于图像辅助的三维模型形状检索

随着3D建模技术的快速发展,互联网上可用的3D模型库出现了爆炸式增长,越来越多的3D模型可以方便地通过网络下载使用.这直接促使了3D形状检索技术的发展,即给出特定的搜索信息,要求系统搜索出符合要求的、相似的3D模型.文章提出了一种新的3D形状检索方法,以3D模型作为输入,系统将会从模型数据库中自动检索出与输入形状最相似的模型.对于给定的输入模型以及数据库中的每一个模型,首先由计算机生成多幅在不同视角下的2D草图;然后,应用Gabor滤波器对每一幅2D草图提取图像上的局部特征,并对特征进行量化,从而得到代表该图像特征的直方图,这样对于每一个3D模型将得到多个代表该模型的直方图;最终,通过对比两个模型之间直方图的相似性,可以得到它们的相似性值,从而检索出与输入模型最相似的模型.文章所提出的方法通过采取2D图像分析方法提取能反映3D模型的特征并计算出模型之间的相似性值.经过测试,在一些公开的数据集上得到了较好的效果.     

利用隐式解码器的三维模型簇协同分割

目的 为建立3维模型语义部件之间的对应关系并实现模型自动分割,提出一种利用隐式解码器（implicit decoder,IM-decoder）的无监督3维模型簇协同分割网络。方法 首先对3维点云模型进行体素化操作,进而由CNN-encoder （convolutional neural network encoder）提取体素化点云模型的特征,并将模型信息映射至特征空间。然后使用注意力模块聚合3维模型相邻点特征,将聚合特征与3维点坐标作为IM-decoder的输入来增强模型的空间感知能力,并输出采样点相对于模型部件的内外状态。最后使用max pooling聚合解码器生成的隐式场,以得到模型的协同分割结果。结果 实验结果表明,本文算法在ShapeNet Part数据集上的mIoU （mean intersection-over-union）为62.1%,与目前已知的两类无监督3维点云模型分割方法相比,分别提高了22.5%和18.9%,分割性能得到了极大提升。与两种有监督方法相比,分别降低了19.3%和20.2%,但其在部件数较少的模型上可获得更优的分割效果。相比于使用交叉熵函数作为重构损失函数,本文使用均方差函数可获得更高的分割准确率,mIoU提高了26.3%。结论 与当前主流的无监督分割算法相比,本文利用隐式解码器进行3维模型簇协同分割的无监督方法分割准确率更高。     

Training deep convolutional neural networks to acquire the best view of a 3D shape

Multimedia Tools and Applications - In a 3D shape retrieval system, when attempting to select the best view from many view images, the ability to project a 3D shape into related view images from...