Clip art rendering of smooth isosurfaces

Clip art is a simplified illustration form consisting of layered filled polygons or closed curves used to convey 3D shape information in a 2D vector graphics format. This paper focuses on the problem of direct conversion of smooth surfaces, ranging from the free-form shapes of art and design to the mathematical structures of geometry and topology, into a clip art form suitable for illustration use in books, papers and presentations.We show how to represent silhouette, shadow, gleam and other surface feature curves as the intersection of implicit surfaces, and derive equations for their efficient interrogation via particle chains. We further describe how to sort, orient, identify and fill the closed regions that overlay to form clip art. We demonstrate the results with numerous renderings used to illustrate the paper itself.     

Coarse‐to‐Fine Normal Filtering for Feature‐Preserving Mesh Denoising Based on Isotropic Subneighborhoods

State‐of‐theart normal filters usually denoise each face normal using its entire anisotropic neighborhood. However, enforcing these filters indiscriminately on the anisotropic neighborhood will lead to feature blurring, especially in challenging regions with shallow features. We develop a novel mesh denoising framework which can effectively preserve features with various sizes. Our idea is inspired by the observation that the underlying surface of a noisy mesh is piecewise smooth. In this regard, it is more desirable that we denoise each face normal within its piecewise smooth region (we call such a region as an isotropic subneighborhood) instead of using the anisotropic neighborhood. To achieve this, we first classify mesh faces into several types using a face normal tensor voting and then perform a normal filter to obtain a denoised coarse normal field. Based on the results of normal classification and the denoised coarse normal field, we segment the anisotropic neighborhood of every feature face into a number of isotropic subneighborhoods via local spectral clustering. Thus face normal filtering can be performed again on the isotropic subneighborhoods and produce a more accurate normal field. Extensive tests on various models demonstrate that our method can achieve better performance than state‐of‐theart normal filters, especially in challenging regions with features.     

快速的人脸轮廓检测及姿态估计算法

提出一种基于人脸特征区域划分的人脸轮廓检测方法和快速人脸姿态估计方法.该方法根据特征点在人脸的分布情况将人脸划分为9个区域.对于每个选定的区域,首先检测出其初始轮廓线,然后用三次多项式对其进行曲线拟合处理,最后把不同区域的轮廓线连接起来得到完整的人脸轮廓.此外,为了快速、准确地估计出人脸的姿态,本文从人脸的对称性出发,提出了进行人脸姿态估计的面积模型和近似平面模型.实验表明,本文所提出的轮廓检测方法对于复杂背景中具有不同姿态的人脸图像可以得到较满意的检测结果.和其它检测方法相比,本文方法具有模型简单、计算速度快等优点.     

Tessellation‐Independent Smooth Shadow Boundaries

We propose an efficient and light‐weight solution for rendering smooth shadow boundaries that do not reveal the tessellation of the shadow‐casting geometry. Our algorithm reconstructs the smooth contours of the underlying mesh and then extrudes shadow volumes from the smooth silhouettes to render the shadows. For this purpose we propose an improved silhouette reconstruction using the vertex normals of the underlying smooth mesh. Then our method subdivides the silhouette loops until the contours are sufficiently smooth and project to smooth shadow boundaries. This approach decouples the shadow smoothness from the tessellation of the geometry and can be used to maintain equally high shadow quality for multiple LOD levels. It causes only a minimal change to the fill rate, which is the well‐known bottleneck of shadow volumes, and hence has only small overhead.     

Visual Analysis of Spatial Variability and Global Correlations in Ensembles of Iso‐Contours

For an ensemble of iso‐contours in multi‐dimensional scalar fields, we present new methods to a) visualize their dominant spatial patterns of variability, and b) to compute the conditional probability of the occurrence of a contour at one location given the occurrence at some other location. We first show how to derive a statistical model describing the contour variability, by representing the contours implicitly via signed distance functions and clustering similar functions in a reduced order space. We show that the spatial patterns of the ensemble can then be derived by analytically transforming the boundaries of a confidence interval computed from each cluster into the spatial domain. Furthermore, we introduce a mathematical basis for computing correlations between the occurrences of iso‐contours at different locations. We show that the computation of these correlations can be posed in the reduced order space as an integration problem over a region bounded by four hyper‐planes. To visualize the derived statistical properties we employ a variant of variability plots for streamlines, now including the color coding of probabilities of joint contour occurrences. We demonstrate the use of the proposed techniques for ensemble exploration in a number of 2D and 3D examples, using artificial and meteorological data sets.     

Appearance Harmonization for Single Image Shadow Removal

Shadow removal is a challenging problem and previous approaches often produce de‐shadowed regions that are visually inconsistent with the rest of the image. We propose an automatic shadow region harmonization approach that makes the appearance of a de‐shadowed region (produced using any previous technique) compatible with the rest of the image. We use a shadow‐guided patch‐based image synthesis approach that reconstructs the shadow region using patches sampled from non‐shadowed regions. This result is then refined based on the reconstruction confidence to handle unique textures. Qualitative comparisons over a wide range of images, and a quantitative evaluation on a benchmark dataset show that our technique significantly improves upon the state‐of‐the‐art.     

Video Shadow Removal Using Spatio‐temporal Illumination Transfer

Shadow removal for videos is an important and challenging vision task. In this paper, we present a novel shadow removal approach for videos captured by free moving cameras using illumination transfer optimization. We first detect the shadows of the input video using interactive fast video matting. Then, based on the shadow detection results, we decompose the input video into overlapped 2D patches, and find the coherent correspondences between the shadow and non‐shadow patches via discrete optimization technique built on the patch similarity metric. We finally remove the shadows of the input video sequences using an optimized illumination transfer method, which reasonably recovers the illumination information of the shadow regions and produces spatio‐temporal shadow‐free videos. We also process the shadow boundaries to make the transition between shadow and non‐shadow regions smooth. Compared with previous works, our method can handle videos captured by free moving cameras and achieve better shadow removal results. We validate the effectiveness of the proposed algorithm via a variety of experiments.     

Extracting eyebrow contour and chin contour for face recognition

This paper proposes a novel method for extraction of eyebrow contour and chin contour. We first segment rough eyebrow regions using spatial constrained sub-area K-means clustering. Then eyebrow contours are extracted by Snake method with effective image force. For chin contour extraction, we first estimate several possible chin locations which are used to build a number of curves as chin contour candidates. Based on the chin like edges extracted by proposed chin edge detector, the curve with the largest likeliness to be the actual chin contour is selected. Finally, the credible extracted eyebrow contour and the estimated chin contours are used as geometric features for face recognition. Experimental results show that the proposed algorithms can extract eyebrow contours and chin contours with good accuracy and the extracted features are effective for improving face recognition rates.     

A 3D face matching framework for facial curves

Among the many 3D face matching techniques that have been developed, are variants of 3D facial curve matching, which reduce the amount of face data to one or a few 3D curves. The face’s central profile, for instance, proved to work well. However, the selection of the optimal set of 3D curves and the best way to match them has not been researched systematically. We propose a 3D face matching framework that allows profile and contour based face matching. Using this framework we evaluate profile and contour types including those described in the literature, and select subsets of facial curves for effective and efficient face matching. With a set of eight geodesic contours we achieve a mean average precision (MAP) of 0.70 and 92.5% recognition rate (RR) on the 3D face retrieval track of the Shape Retrieval Contest (SHREC’08), and a MAP of 0.96 and 97.6% RR on the University of Notre Dame (UND) test set. Face matching with these curves is time-efficient and performs better than other sets of facial curves and depth map comparison.     

A generic and parallel algorithm for 2D digital curve polygonal approximation

In this paper, we present a generic topological and geometrical framework which allows to define and control several parallel algorithms for 2D digital curve approximation. The proposed technique is based on combinatorial map simplifications guided by geometrical criteria. We illustrate the genericity of the framework by defining three contour simplification methods: a polygonal approximation one based an area deviation computation; a digital straight segments reconstruction one which guaranties to obtain a loss-less representation; and a moment preserving simplification one which simplifies the contours while preserving geometrical moments of the image regions. Thanks to a complete experimental evaluation, we demonstrate that the proposed methods can be efficiently implemented in a multi-thread environment to simplify labeled image contours.     

A new graph cut-based multiple active contour algorithm without initial contours and seed points

This paper presents a new graph cut-based multiple active contour algorithm to detect optimal boundaries and regions in images without initial contours and seed points. The task of multiple active contours is framed as a partitioning problem by assuming that image data are generated from a finite mixture model with unknown number of components. Then, the partitioning problem is solved within a divisive graph cut framework where multi-way minimum cuts for multiple contours are efficiently computed in a top-down way through a swap move of binary labels. A split move is integrated into the swap move within that framework to estimate the model parameters associated with regions without the use of initial contours and seed points. The number of regions is also estimated as a part of the algorithm. Experimental results of boundary and region detection of natural images are presented and analyzed with precision and recall measures to demonstrate the effectiveness of the proposed algorithm.     

3D Shape Segmentation and Labeling via Extreme Learning Machine

We propose a fast method for 3D shape segmentation and labeling via Extreme Learning Machine (ELM). Given a set of example shapes with labeled segmentation, we train an ELM classifier and use it to produce initial segmentation for test shapes. Based on the initial segmentation, we compute the final smooth segmentation through a graph‐cut optimization constrained by the super‐face boundaries obtained by over‐segmentation and the active contours computed from ELM segmentation. Experimental results show that our method achieves comparable results against the state‐of‐the‐arts, but reduces the training time by approximately two orders of magnitude, both for face‐level and super‐face‐level, making it scale well for large datasets. Based on such notable improvement, we demonstrate the application of our method for fast online sequential learning for 3D shape segmentation at face level, as well as realtime sequential learning at super‐face level.     

等高线图的高度恢复算法研究

用于等高线图到数字高度图（Digital Elevation Map)转换的转换算法是很多应用都需要的算法，为了提高这一转换的精度与效率，一个相应的算法－区域内插法被特别提出来，该算法利用了等高线图固有的特性，即“图象被等高线分割成多个区域，每个区域内的边界只有两个等高线值”的特性，该算法可以在计算机上快速实现，经过与现有的象限搜索法的实验比较，由于它更好地利用了等高线图结构上的特点，致使其在提高速度的同时，精度上较象限搜索法也有很大的提高，因而具有很强的实用价值。     

一种由轮廓线重建物体表面的方法

针对基于轮廓线拼接重建物体表面所出现的轮廓对应和分叉问题,提出了一种通过体数据转换由轮廓线实现重建物体表面的方法。在分析体数据构造中出现逼近精度问题的前提下,通过提高轮廓线上点的密度,生成精确度较高的体数据。该方法通过对相邻层轮廓线区域的集合运算,只对处于集合运算解中的像素点进行距离函数值的计算。采用MC（Marching Cubes）算法生成等值面,完成物体的表面重建。实验结果表明,该方法能顺利解决基于轮廓线拼接重建物体表面中出现的轮廓对应问题和分叉问题,既提高重建表面精确度,又加快整个表面的重建速度,是一种可行的方法。     

Acquiring 3-D models from sequences of contours

This paper explores shape from contour for acquiring 3-D graphics models. In this method, a continuous sequence of images is taken as an object rotates. A smooth convex shape can be estimated instantaneously from its contour and by the first derivative of contour movement (trace of contour, or contour distribution with time). We also analyze shapes that do not satisfy the conditions of smoothness and visibility, which are indispensable for modeling an object. A region that does not expose as contour yields a nonsmoothness in the tracked contour movement. We can thus detect such a region by contour distribution filtering and extract its accurate location by computing the left and right derivatives of the distribution. This has not been studied previously. These unknown regions are obtained for further investigation using other visual cues. A general approach for building a geometrical object model using contours is then described. The entire process from silhouettes to a 3-D model is based local computation; this is promising for producing shapes in real time. Our direct goal is to establish 3-D graphics models of human faces for the growing needs of visual communications. We have obtained some good results     

基于轮廓特征的人体行为识别

提出了一种以人的动作序列图像的轮廓为特征、基于隐条件随机场的行为识别方法。首先,利用背景差分法 和阴影消除技术提取运动人体轮廓。星型骨架方法只采用单一质心一边界距离来描述人体轮廓,因此对轮廓的局部特 征描述能力较弱。定义一种新的基于距离组的轮廓描述方法,它将时变的2D轮廓形状转换为对应的1D距离向量。 最后利用判别隐条件随机场对行为进行训练和识别。实验结果表明,本方法的正确识别率达到91. 4%以上,识别结 果较为理想。     

基于特征点表情变化的3维人脸识别

目的 为克服表情变化对3维人脸识别的影响,提出一种基于特征点提取局部区域特征的3维人脸识别方法。方法 首先,在深度图上应用2维图像的ASM(active shape model)算法粗略定位出人脸特征点,再根据Shape index特征在人脸点云上精确定位出特征点。其次,提取以鼻中为中心的一系列等测地轮廓线来表征人脸形状;然后,提取具有姿态不变性的Procrustean向量特征(距离和角度)作为识别特征;最后,对各条等测地轮廓线特征的分类结果进行了比较,并对分类结果进行决策级融合。结果 在FRGC V2.0人脸数据库分别进行特征点定位实验和识别实验,平均定位误差小于2.36 mm,Rank-1识别率为98.35%。结论 基于特征点的3维人脸识别方法,通过特征点在人脸近似刚性区域提取特征,有效避免了受表情影响较大的嘴部区域。实验证明该方法具有较高的识别精度,同时对姿态、表情变化具有一定的鲁棒性。     

Hybrid path planning method based on skeleton contour partitioning for robotic additive manufacturing

Establishing manufacturability design criteria for multidimensional complex parts can significantly reduce the production cost, shorten the manufacturing cycle, and improve the production quality of directed energy deposition. Therefore, there is an urgent need to establish a high-performance manufacturing design strategy for complex parts. Proposed here is a skeleton contour partitioning hybrid path-planning method that takes full advantage of the excellent geometric reducibility of the contour offset method and the outstanding flexibility of the zigzag path method, eliminating the influences of sharp corners and degradation on forming quality in the contour offset method. First, reference contours are obtained by subjecting the original contours to an inward–outward twice-offset process; incompletely filled regions are obtained by Boolean operations on the original and reference contours, and these regions are the ones to be optimized. Second, the optimized regions are merged into skeleton fill regions, and the fill paths are generated by a polygon trapezoidal partitioning recombination algorithm and an algorithm for generating optimal zigzag paths. Finally, the contour offset paths are split and regrouped based on the skeleton regions and are connected into a continuous forming path for each subregion, then all the forming paths are converted into robot printing tool paths from the skeleton-region filling paths to the contour-offset ones. The actual forming results for several parts with different geometric features are verified and compared with those of the traditional path-planning method, and it is concluded that the proposed method converges rapidly to the details of complex components and is highly feasible and applicable.     

2D‐D Lifting for Shape Reconstruction

We present an algorithm for shape reconstruction from incomplete 3D scans by fusing together two acquisition modes: 2D photographs and 3D scans. The two modes exhibit complementary characteristics: scans have depth information, but are often sparse and incomplete; photographs, on the other hand, are dense and have high resolution, but lack important depth information. In this work we fuse the two modes, taking advantage of their complementary information, to enhance 3D shape reconstruction from an incomplete scan with a 2D photograph. We compute geometrical and topological shape properties in 2D photographs and use them to reconstruct a shape from an incomplete 3D scan in a principled manner. Our key observation is that shape properties such as boundaries, smooth patches and local connectivity, can be inferred with high confidence from 2D photographs. Thus, we register the 3D scan with the 2D photograph and use scanned points as 3D depth cues for lifting 2D shape structures into 3D. Our contribution is an algorithm which significantly regularizes and enhances the problem of 3D reconstruction from partial scans by lifting 2D shape structures into 3D. We evaluate our algorithm on various shapes which are loosely scanned and photographed from different views, and compare them with state‐of‐the‐art reconstruction methods.     

基于照度补偿的人脸图像遮挡阴影消除处理*

为了消除人脸图像中的遮挡阴影对识别精度的影响,采用数学形态学处理对阴影进行检测分离,根据其照度损失不同划分为阴影边缘区和阴影主体区,分别实施照度补偿,并将非阴影区、阴影边缘区和阴影主体区光强光顺过渡,实现对图像阴影区域的恢复处理。基于该照度补偿原理处理实例表明,该方法可以较好地去除人脸图像中部因遮挡造成的阴影,显著改善图像质量。