Approximate Symmetry Detection in Partial 3D Meshes

Symmetry is a common characteristic in natural and man‐made objects. Its ubiquitous nature can be exploited to facilitate the analysis and processing of computational representations of real objects. In particular, in computer graphics, the detection of symmetries in 3D geometry has enabled a number of applications in modeling and reconstruction. However, the problem of symmetry detection in incomplete geometry remains a challenging task. In this paper, we propose a vote‐based approach to detect symmetry in 3D shapes, with special interest in models with large missing parts. Our algorithm generates a set of candidate symmetries by matching local maxima of a surface function based on the heat diffusion in local domains, which guarantee robustness to missing data. In order to deal with local perturbations, we propose a multi‐scale surface function that is useful to select a set of distinctive points over which the approximate symmetries are defined. In addition, we introduce a vote‐based scheme that is aware of the partiality, and therefore reduces the number of false positive votes for the candidate symmetries. We show the effectiveness of our method in a varied set of 3D shapes and different levels of partiality. Furthermore, we show the applicability of our algorithm in the repair and completion of challenging reassembled objects in the context of cultural heritage.     

Keypoint Detection and Local Feature Matching for Textured 3D Face Recognition

In this study we concentrate on qualitative topological analysis of the local behavior of the space of natural images. To this end, we use a space of 3 by 3 high-contrast patches ℳ. We develop a theoretical model for the high-density 2-dimensional submanifold of ℳ showing that it has the topology of the Klein bottle. Using our topological software package PLEX we experimentally verify our theoretical conclusions. We use polynomial representation to give coordinatization to various subspaces of ℳ. We find the best-fitting embedding of the Klein bottle into the ambient space of ℳ. Our results are currently being used in developing a compression algorithm based on a Klein bottle dictionary.     

Performance Evaluation of 3D Keypoint Detectors

In the past few years detection of repeatable and distinctive keypoints on 3D surfaces has been the focus of intense research activity, due on the one hand to the increasing diffusion of low-cost 3D sensors, on the other to the growing importance of applications such as 3D shape retrieval and 3D object recognition. This work aims at contributing to the maturity of this field by a thorough evaluation of several recent 3D keypoint detectors. A categorization of existing methods in two classes, that allows for highlighting their common traits, is proposed, so as to abstract all algorithms to two general structures. Moreover, a comprehensive experimental evaluation is carried out in terms of repeatability, distinctiveness and computational efficiency, based on a vast data corpus characterized by nuisances such as noise, clutter, occlusions and viewpoint changes.     

3D物体检测的异构方法

3D物体检测是计算机视觉的一个重要研究方向,在自动驾驶等领域有着广泛的应用.现有的前沿工作采用端到端的深度学习方法,虽然达到了很好的检测效果但存在着算法复杂度高、计算量大、实时性不够等问题.经过分析发现3D物体检测中的“部分任务”并不适合使用深度学习的方法进行解决,为此提出了一种基于异构方法的3D物体检测方法,该方法在检测过程中同时使用深度学习和传统算法,将检测过程划分为多任务阶段：1)利用深度学习方法从被检测图片中获取被检测物体的mask、物体类别等信息;2)基于mask,利用快速聚类方法从雷达点云空间中筛选出目标物体的表面雷达点;3)利用物体mask、类别、雷达点云等信息计算物体朝向、边框等信息,最终实现3D物体检测.对该方法进行了系统实现,称之为HA3D(a heterogeneous approach for 3D object detection).经实验表明：在针对汽车的3D检测数据集KITTI上,该方法与代表性的基于深度学习的3D物体检测方法相比,在检测精度下降接受范围内(2.0%),速度提升了52.2%,精确率与计算时间的比值提升了49%.从综合表现上来看,方法具有明显的优势.     

面向3D网格模型的多重数字水印算法

为了解决单盲水印网格算法难以抵抗多种攻击的问题,提出一种鲁棒的3D网格模型的多重数字水印算法.该算法分别对3D网格模型的顶点信息和拓扑信息嵌入2种不同类型的单鲁棒性水印,从而使模型既能抵抗大面积的剪切攻击,又能抗击一定强度的噪声攻击;且在水印提取时不需要原始模型信息.实验结果表明,该算法能有效地提高水印抗平移、旋转、缩放、非均匀缩放、剪切、噪声和顶点乱序等攻击的能力.     

3D Keypoint Estimation Using Implicit Representation Learning

In this paper, we tackle the challenging problem of 3D keypoint estimation of general objects using a novel implicit representation. Previous works have demonstrated promising results for keypoint prediction through direct coordinate regression or heatmap-based inference. However, these methods are commonly studied for specific subjects, such as human bodies and faces, which possess fixed keypoint structures. They also suffer in several practical scenarios where explicit or complete geometry is not given, including images and partial point clouds. Inspired by the recent success of advanced implicit representation in reconstruction tasks, we explore the idea of using an implicit field to represent keypoints. Specifically, our key idea is employing spheres to represent 3D keypoints, thereby enabling the learnability of the corresponding signed distance field. Explicit key-points can be extracted subsequently by our algorithm based on the Hough transform. Quantitative and qualitative evaluations also show the superiority of our representation in terms of prediction accuracy.     

Embedding Pyramids into 3D Meshes

The pyramid architecture is a powerful topology in the area of computer vision. On the other hand, the 3D mesh architecture possesses rich topological features which make it suitable for building scalable parallel processor systems. The usefulness of these two architectures has led us to consider the problem of embedding pyramids into 3D meshes, for which we present two solutions. The first solution, termednatural embedding,maps a pyramid into a 3D mesh such that each level of the pyramid is mapped to a single level of the 3D mesh. The second solution, termedmultiple embedding,allows simultaneous embedding of multiple pyramids into a single 3D mesh. The quality of both solutions is evaluated using dilation and expansion measures. Using the multiple embedding, we are able to obtain an average dilation of 1.26 and a near-optimal expansion of 1.12.     

基于关键点检测的无锚框轻量级目标检测算法

针对基于关键点的目标检测参数量大、检测框误匹配的问题,提出一种轻量级的基于关键点检测的无锚框目标检测算法.首先将输入图片输入优化过的特征提取算法,通过级联角池化与中心池化,输出3个关键点的热力图与它们的嵌入向量;然后通过嵌入向量匹配热力图并画出检测框.文中的创新点在于将SqueezeNet中的轻量级模块firemodu...     

Interactive Planarization and Optimization of 3D Meshes

Constraining 3D meshes to restricted classes is necessary in architectural and industrial design, but it can be very challenging to manipulate meshes while staying within these classes. Specifically, polyhedral meshes—those having planar faces—are very important, but also notoriously difficult to generate and manipulate efficiently. We describe an interactive method for computing, optimizing and editing polyhedral meshes. Efficiency is achieved thanks to a numerical procedure combining an alternating least‐squares approach with the penalty method. This approach is generalized to manipulate other subsets of polyhedral meshes, as defined by a variety of other constraints.     

曲面浅浮雕生成算法

为了在三维网格上快速生成曲面浅浮雕造型,提出一种利用三维模型半自动生成曲面浅浮雕的算法.首先利用图像的边缘检测方法来获取模型在透视场景中的边缘点,并将其与被贴的曲面载体进行位置匹配,获得Poisson方程的Dirichlet边界值;然后对模型高度场的梯度值进行压缩;最后利用确定边界条件的Poisson方程对模型压缩后的梯度场进行求解,还原生成浮雕模型.利用文中算法可以生成贴于曲面上的浅浮雕模型.     

不可逆的3维网格模型数字水印算法

提出一种基于奇异值分解的三角网格模型数字水印算法,该算法主要思想在于把水印信息嵌入到奇异值为零的地方,由于零值的特点使得算法不可逆,从而成功抵御了解释攻击。该算法简单,并可以快速嵌入到大规模三角网格模型里。通过几种不同的攻击实验,验证了算法具有很好的鲁棒性,最后还对构造不可逆算法的必要条件进行了总结。     

鲁棒估计器在3D网格降噪中的应用

从最小平方估计的观点揭示了最小平方估计与Laplacian光顺算法之间的关联,并进一步提出了M-估计器在网格光顺中的应用,最后延伸M-估计器至二次加权的M-估计器,在抑制噪声的同时有效地保持了表面特征.在本质上,二次加权的M-估计器就是双向滤波器.     

Triangulation on Reconfigurable Meshes: A Natural Decomposition Approach

Central to many algorithms for reconfigurable meshes (R-meshes) is the method of divide-and-conquer (DAC). Although there is no provision in this method per se that a problem must be divided into subproblems evenly in size, in practice almost all existing DAC-based R-mesh algorithms divide problems in this fashion. This paper demonstrates that dividing a problem evenly is not necessarily a good approach. For some problems, a natural decomposition scheme may be preferable, in which a problem is divided into subproblems along their "natural" boundaries, often resulting in an irregular decomposition. Taking this approach, we obtain a new R-mesh algorithm that triangulates a set of points on O(1) time. This algorithm is simpler than existing ones. We also obtain an R-mesh algorithm for simple-polygon triangulation, the first such algorithm for this problem.     

A Frequency-Domain Approach to Watermarking 3D Shapes

This paper presents a robust watermarking algorithm with informed detection for 3D polygonal meshes. The algorithm is based on our previous algorithm [ 22 ] that employs mesh‐spectral analysis to modify mesh shapes in their transformed domain. This paper presents extensions to our previous algorithm so that (1) much larger meshes can be watermarked within a reasonable time, and that (2) the watermark is robust against connectivity alteration (e.g., mesh simplification), and that (3) the watermark is robust against attacks that combine similarity transformation with such other attacks as cropping, mesh simplification, and smoothing. Experiment showed that our new watermarks are resistant against mesh simplification and remeshing combined with resection, similarity transformation, and other operations..     

Valence-Driven Connectivity Encoding for 3D Meshes

In this paper, we propose a valence-driven, single-resolution encoding technique for lossless compression of triangle mesh connectivity. Building upon a valence-based approach pioneered by Touma and Gotsman²² , we design a new valence-driven conquest for arbitrary meshes that always guarantees smaller compression rates than the original method. Furthermore, we provide a novel theoretical entropy study of our technique, hinting the optimality of the valence-driven approach. Finally, we demonstrate the practical efficiency of this approach (in agreement with the theoretical prediction) on a series of test meshes, resulting in the lowest compression ratios published so far, for both irregular and regular meshes, small or large.     

Optimized Topological Surgery for Unfolding 3D Meshes

Constructing a 3D papercraft model from its unfolding has been fun for both children and adults since we can reproduce virtual 3D models in the real world. However, facilitating the papercraft construction process is still a challenging problem, especially when the shape of the input model is complex in the sense that it has large variation in its surface curvature. This paper presents a new heuristic approach to unfolding 3D triangular meshes without any shape distortions, so that we can construct the 3D papercraft models through simple atomic operations for gluing boundary edges around the 2D unfoldings. Our approach is inspired by the concept of topological surgery, where the appearance of boundary edges of the unfolded closed surface can be encoded using a symbolic representation. To fully simplify the papercraft construction process, we developed a genetic‐based algorithm for unfolding the 3D mesh into a single connected patch in general, while optimizing the usage of the paper sheet and balance in the shape of that patch. Several examples together with user studies are included to demonstrate that the proposed approach works well for a broad range of 3D triangular meshes.     

基于几何特征的3维网格模型零水印算法

由于3维网格模型对水印嵌入强度高度敏感,为避免外观视觉效果严重失真,如今多数水印算法只能采用低强度的嵌入策略,从而导致其鲁棒性能下降。为了解决水印鲁棒性和透明性之间的矛盾问题,提出了一种不对网格模型数据进行任何改动的零水印算法。该方法首先对网格模型的几何数据进行校准预处理,然后对网格按顶点包围盒进行分割来提取几何数据空域特征,进而再应用3维DCT变换在变换域中进一步集中能量,其水印由若干DCT大值系数构造生成,并在IPR数据库注册获得版权保护,该水印的检测过程无需原始网格模型数据的参与。实验结果表明,该算法构造的水印不仅能抵抗顶点重排序、平移、旋转、各向一致缩放等攻击,而且对加噪、网格简化、网格滤波和二次水印等也表现出一定的鲁棒性。     

基于轻量级网络的实时人体关键点检测算法

为提升人体姿态估计在移动终端设备上的运行速度与实时性,提出一种改进的人体关键点检测算法.通过将MobileNetV2轻量级主干网络与深度可分离卷积模块相结合加速特征提取过程,使用精炼网络进行多尺度人体关键点预测,并利用融合网络整合多个尺度的预测结果得到最终人体关键点检测结果.实验结果表明,与传统CPM算法相比,该算法在...