Detail-generating geometry completion for point-sampled geometry

In this paper, we present a novel method for detail-generating geometry completion over point-sampled geometry. The main idea consists of converting the context-based geometry completion into the detail-based texture completion on the surface. According to the influence region of boundary points surrounding a hole, a smooth patch covering the hole is first constructed using radial base functions. By applying region-growing clustering to the patch, the patching units for further completion with geometry details is then produced, and using the trilateral filtering operator formulated by us, the geometry-detail texture of each sample point on the input geometry is determined. The geometry details on the smooth completed patch are finally generated by optimizing a constrained global texture energy function on the point-sampled surfaces. Experimental results demonstrate that the method can achieve efficient completed patches that not only conform with their boundaries, but also contain the plausible 3D surface details.     

A unified method for appearance and geometry completion of point set surfaces

This paper presents a novel approach for appearance and geometry completion over point-sampled geometry. Based on the result of surface clustering and a given texture sample, we define a global texture energy function on the point set surface for direct texture synthesis. The color texture completion is performed by minimizing a constrained global energy using the existing surface texture on the surface as the input texture sample. We convert the problem of context-based geometry completion into a task of texture completion on the surface. The geometric detail is then peeled and converted into a piece of signed gray-scale texture on the base surface of the point set surface. We fill the holes on the base surface by smoothed extrapolation and the geometric details over these patches are reconstructed by a process of gray-scale texture completion. Experiments show that our method is flexible, efficient and easy to implement. It provides a practical texture synthesis and geometry completion tool for 3D point set surfaces.     

Geometry completion and detail generation by texture synthesis

We present a novel method for patching holes in polygonal meshes and synthesizing surfaces with details based on existing geometry. The most novel feature of our proposed method is that we transform the 3D geometry synthesis problem into a 2D domain by parameterizing surfaces and solve this problem in that domain. We then derive local geometry gradient images that encode intrinsic local geometry properties, which are invariant to object translation and rotation. The 3D geometry of holes is then reconstructed from synthesized local gradient images. This method can be extended to execute other mesh editing operations such as geometry detail transfer or synthesis. The resulting major benefits of performing geometry synthesis in 2D are more flexible and robust control, better leveraging of the wealth of current 2D image completion methods, and greater efficiency.     

快速结构化图像修补

图像修补的目的是对图像中缺失的区域进行修复,或是将图像中的物体抠去并进行背景填充,以取得融合到难以用肉眼分辨的效果。在图像修补的过程中,较大的结构信息是修补的难点。为此提出了一种快速结构化的图像修补算法,该方法将图像修补分为结构修补与纹理填充两个部分,即在用户指定待修补区域与结构曲线之后,首先定义全局最优化能量函数,并用动态规划与置信度传播的算法将其最小化来完成结构修补;然后对剩余的待修补区域通过按行扫描来进行纹理填充,其中对于边界处的点是使用基于样本的修补算法,而对于待修补区域内部的点,则使用快速的加权Ashikhmin-WL算法,扫描完成后输出修补后的图像;最后实现了一个快速结构化图像修补系统,并给出一些实验结果,从实验结果中可以看到,该方法的修补流程与算法是有实际应用价值的。     

Truly naked black holes and quasi-black holes

Usually, a black hole horizon hides singularities beyond it, being itself perfectly regular. We discuss somewhat unusual cases when the system can combine regular and singular features due to the presence of the horizon. The first example concerns the so-called truly naked black holes, when the Kretschmann scalar is finite but tidal forces diverge at the horizon in the freely falling frame. The second one concerns the so-called quasi-black holes, a special kind of objects on the verge of forming extremal black holes. Then, a “naked” behavior can occur in the entire region beyond the quasi-horizon. Apart from this, there is another kind of singular behavior in this case due to the quasi-horizon. In particular, this concerns the simplest example with a charged massive shell empty inside. The curvature inside is zero, but the whole inner region becomes degenerate in the quasi-horizon limit. Talk given at the Russian School-Seminar on Modern Problems of Gravitation and Cosmology, Kazan-Yal’chik, 10–15 September 2007.     

网格修补的特征配准方法

目的 网格重建和编辑会产生几何特征缺失的模型,填补这些空洞具有重要的意义。为了克服复杂曲面修补中网格融合难以配准的问题,提出了环驱动球坐标结合基于曲率及法向ICP(iterative closest point)迭代配准的网格修补方法。方法 首先用户查找合适的源网格面片放入空洞处周围;然后对目标网格空洞环建立B样条曲线,将带修补网格包边界置于B样条曲线上,构架环驱动球坐标,将源网格变形初步配准目标网格空洞周围领域;最后使用Laplacian光顺并基于网格曲率及法向进行ICP迭代配准,使源网格与目标网格光滑拼接融合。结果 该方法能够有效修补网格空洞缺失的细节特征,并且拼接处光滑连续。 结论 环驱动球坐标配准避免了网格变形的包围网格笼子构造,再通过ICP迭代精确配准网格,和以往的网格修补方法相比,该方法能够很好地修补网格空洞处细节特征。     

Linguistic diversity and information poverty in South Asia and Sub-Saharan Africa

This communication starts with a fundamental question that drives the actions of most local and global policy-makers: out of two categories of people (not mutually exclusive), the ‘have nots’ and the ‘know nots’, which one is more difficult to eradicate (one may pose the question differently—solving which of these two problems is likely to solve the other). A lot of attention and resources have been deployed and are committed on the challenge of uplifting the ‘have nots’ to the section of bare minimum ‘haves’ category. A cause and effect study between these two sections of people essentially show a mutual dependency that eventually leads to a vicious cycle of poverty to information poverty to back again poverty which has historically been difficult to eradicate, and studies have often established education and access to timely information to be a long term sustainable remedy to both these perpetual problems. The role that the Internet can play in this background towards empowering the billions of impoverished across two of the most underdeveloped regions, namely South Asia (SA) and Sub-Saharan Africa (SSA), home to world’s largest number of illiterates and poor people (70% or even more together) is immense. With anywhere, anytime accessibility of rich Internet content, aided by its falling prices and increased connectivity and easy to use features, to parts of rural and even to inaccessible remote areas, online content can effectively act as a low-cost feasible solution not only to provide basic education, but also to deliver meaningful information and content to the millions of primary-level educated people within the underprivileged sections of SA & SSA, thereby enabling them to integrate and exploit various socio-economic opportunities arising from growth in global economies. However, rich linguistic diversity, both in SA and SSA, poses a challenge to that opportunity. Content development to information access to literacy, all leading to socio-economic developments, do face additional difficulties arising from linguistic diversity for SA and SSA, regions already plagued with low level of content generation and access in local languages. A closer examination of the ‘sea’ of online content reveals that SA scores poorly in local language content development, whereas English is primarily used for Internet usage, though nearly 90% of people of India do not use English as a 2nd or 3rd languages. For SSA, a study reported here qualitatively examines whether linguistic diversity indeed has any negative correlations with gross national income and Internet penetration, and finds that they indeed are inversely related in 80% or more cases. One case-effort is also examined to develop local language content, critical to reap benefits from content for development for SA and SSA, in South Asia, but it was found to be inadequate in proportion to the severity and scale of the problem. It is alarmingly concluded that unless war-footing action is adopted to generate relevant local language content (or effectively supported by software like Google Translation) in the linguistically diverse backward regions of the world, much of the benefits that could have been derived from increased reach of freely available online content would be lost, causing an escalation of information poverty to the ‘bottom of the pyramid’ section of people in South Asia and Sub-Saharan Africa. Ranjit Goswami is also a faculty member with Indian Institute of Foreign Trade, Kolkata, India.     

不规则块的图像补全算法

目的 目前在图像补全领域研究的重点和难点是补全具有复杂结构信息和丰富纹理信息的大破损区域的图像。传统的基于样本块的图像补全算法主要采用规则的模板块和匹配块来进行补全,补全过程中不能充分利用图像的结构或纹理的不规则信息,从而影响算法修复的精度和效率。针对这一问题,本研究提出一种基于不规则块的图像补全算法。方法 在该算法中,首先利用结构稀疏度来区分图像的结构信息和纹理信息并基于结构稀疏度和置信度计算破损区域边界点的优先级,然后选择优先级最高的点构造规则模板块。对处于复杂结构区域的模板块,如果其邻域含有已知的结构信息,则膨胀该规则模板并利用其周围的结构信息来辅助构造不规则模板块。接下来,在图像完好区域内搜索与该模板块对应的匹配块,如果该匹配块的邻域包含有效的结构信息,则膨胀该匹配块并补充其周围的结构信息来完善该不规则匹配块。最后,利用该不规则匹配块补全破损区域。对于补全过程中块间接缝造成的视觉不连通问题,本研究利用图像的纹理信息来进行修饰。结果 将本文算法与4种修复效果较好的算法（3种基于规则块的算法和1种基于局部敏感哈希的修复算法）进行对比,通过8组经典图像进行实例验证,采用客观评价指标峰值信噪比PSNR和主观视觉连通性进行评价,结果表明本文提出的算法峰值信噪比相较4种对比算法均有04 dB的提高,且在补全的精细度和视觉连通性方面有更佳的效果。结论 本文算法在补全含有较复杂结构和丰富纹理的破损自然图像、壁画图像和目标物体移除上有较好的修复效果,普适性较强。     

A note on pathria’s model of the universe as a black hole

Pathria has shown that, for the certain values of the cosmological constant, a pressureless closed Friedmann-Robertson-Walker universe can be the interior of a Schwarzschild black hole. We examine Pathria’s model from the point of view of matching of two different spacetimes through a null hypersurface. We first regard the event horizon of the black hole, which in Pathria’s model is identified with the radius of the universe at the point of its maximum expansion, as a null hypersurface separating the FRW interior from the vacuum Schwarzschild exterior, and then use the null shell formalism for it. It turns out that matching is not smooth, and in fact, the null hypersurface is the history of a null shell admitting a surface pressure.     

三维重建网格模型的缺陷孔洞识别与修复方法

针对三维重建网格模型经常出现异常缺失孔洞的问题,提出一种缺陷孔洞自动识别与孔洞区域细节特征保持的曲面修复方法。首先对缺失区域的上下文及轮廓曲线进行异常检测以判断是否为缺陷孔洞, 确认为缺陷孔洞后对孔洞周边的特征线进行检测与匹配构造孔洞区域的基曲面;之后引进一个无约束的三角剖分对基曲面进行三角化;最后利用网格的各向异性进行细化及形态调整,改善网格的拓扑结构和几何性质。实验结果表明,该方法能够有效地识别三角网格模型的缺陷孔洞区域并还原其细节特征。     

沿法线方向传播的深度图像补洞算法

密集的深度信息在计算机视觉的各种任务中有广泛的应用,然而深度相机在有光泽、透明、较远处的物体表面通常无法探测到深度信息,映射到深度图片上形成了大小不一的孔洞。因此,提出了一种沿法线方向传播的单一深度图像补洞算法。本文方法沿着物体本身的曲面变化进行扩散,把深度图片的补全问题转化成几何完成的问题。首先把2D的深度图像扩展到3D点云,然后3D点云沿着孔洞边界的法线方向向内收缩。收缩的过程中加入类似正态滤波器的约束函数来模拟深度的变化,使填充的点云更加适合整个物体的结构。最后把3D点云重新映射到2D图片上。本文的算法在NYU-Depth-v2数据集上进行测试,实验证明本文算法对孔洞的填充有较好的效果。     

A triangulation-based hole patching method using differential evolution

In this work, a new hole patching method (namely as, HPDE) is proposed to repair the damaged or ill-scanned three dimensional objects in real engineering applications. Our method differentiates from other related algorithms mainly on the following three aspects. Firstly, our algorithm sufficiently utilizes the point information around the considered hole for each prediction by constructing point correspondences on both sides of the boundary curve of the hole; secondly, the missing points in the hole region are predicted by the algorithm of differential evolution (DE), which is used to obtain the topological and geometrical structures of the mesh in the hole region; thirdly, operations of mesh optimization are adopted for improving the quality of the obtained triangulation mesh. Numerical results on kinds of holes with complex shape and large curvature, and a comparison with two recently proposed algorithms verify the effectiveness of the algorithm, further experiments on the noisy data points illustrate the robustness of the algorithm against noise.     

Video completion using tracking and fragment merging

Video completion is the problem of automatically filling space–time holes in video sequences left by the removal of unwanted objects in a scene. We solve it using texture synthesis, filling a hole inwards using three steps iteratively: we select the most promising target pixel at the edge of the hole, we find the source fragment most similar to the known part of the target’s neighborhood, and we merge source and target fragments to complete the target neighborhood, reducing the size of the hole. Earlier methods were slow, due to searching the whole video data for source fragments or completing holes pixel by pixel; they also produced blurred results due to sampling and smoothing. For speed, we track moving objects, allowing us to use a much smaller search space when seeking source fragments; we also complete holes fragment by fragment instead of pixelwise. Fine details are maintained by use of a graph cut algorithm when merging source and target fragments. Further techniques ensure temporal consistency of hole filling over successive frames. Examples demonstrate the effectiveness of our method.     

Fluid in Video: Augmenting Real Video with Simulated Fluids

We present a technique for coupling simulated fluid phenomena that interact with real dynamic scenes captured as a binocular video sequence. We first process the binocular video sequence to obtain a complete 3D reconstruction of the scene, including velocity information. We use stereo for the visible parts of 3D geometry and surface completion to fill the missing regions. We then perform fluid simulation within a 3D domain that contains the object, enabling one‐way coupling from the video to the fluid. In order to maintain temporal consistency of the reconstructed scene and the animated fluid across frames, we develop a geometry tracking algorithm that combines optic flow and depth information with a novel technique for “velocity completion”. The velocity completion technique uses local rigidity constraints to hypothesize a motion field for the entire 3D shape, which is then used to propagate and filter the reconstructed shape over time. This approach not only generates smoothly varying geometry across time, but also simultaneously provides the necessary boundary conditions for one‐way coupling between the dynamic geometry and the simulated fluid. Finally, we employ a GPU based scheme for rendering the synthetic fluid in the real video, taking refraction and scene texture into account.     

A black hole novelty detector for video analysis

A black hole is a region of space that has so much mass concentrated in it that there is no way training data for a nearby object to escape its gravitational pull. In this paper we are inspired by this phenomenon to create a new form of novelty detector. We consider the of a given class as a black hole. For multi-class data we are dealing with multiple black holes. A test point is pulled by the centroids of different black holes as well as its K nearest neighbours. The gravitational pull is modelled as an iterative process, where the forces acting on a point are constantly changing with time as the test point moves in multi-dimensional space corresponding to these forces. Once the algorithm has converged, a thresholding scheme is applied to determine whether the test point has been pulled within the boundary of the black hole or not. Any points that lie outside all known black holes are deemed to be novel. We compare this novelty detector with other well-known models of novelty detection on a video analysis application and show very promising results.     

Tool condition classification using Hidden Markov Model based on fractal analysis of machined surface textures

The texture of a machined surface generated by a cutting tool, with geometrically well-defined cutting edges, carries essential information regarding the extent of tool wear. There is a strong relationship between the degree of wear of the cutting tool and the geometry imparted by the tool on to the workpiece surface. The monitoring of a tool’s condition in production environments can easily be accomplished by analyzing the surface texture and how it is altered by a cutting edge experiencing progressive wear and micro-fractures. This paper discusses our work which involves fractal analysis of the texture of surfaces that have been subjected to machining operations. Two characteristics of the texture, high directionality and self-affinity, are dealt with by extracting the fractal features from images of surfaces machined with tools with different levels of tool wear. The Hidden Markov Model is used to classify the various states of tool wear. In this paper, we show that fractal features are closely related to tool condition and HMM-based analysis provides reliable means of tool condition prediction.     

A hybrid-based texture synthesis approach

Texture synthesis has been an active research area in computer graphics, vision, and image processing. A hybrid texture synthesis approach that combines the strength of Ashikhmins [1] and Liangs [11] algorithms is presented in this paper. Using patches from the input sample texture to extend the input itself, more suitable valid candidate pixels in the input sample can be more precisely determined. An extra original position array is used to record the valid pixel position in the extended region of input sample texture such that the candidate pixel can be retrieved efficiently. Pasting patches with more global information of texture features to initialize the output texture, the texture synthesis process tends to grow larger pieces in the output texture so that the perceptual similarity is reserved as much as possible. Many classes of textures have been used to test our approach. As the experimental results showed, the proposed hybrid approach effectively and efficiently synthesizes high-quality textures from a wide variety of textures.     

Evaluation of texture registration by epipolar geometry

In the process of digitizing the geometry and appearance of 3D objects, texture registration is a necessary step that solves the 2D–3D mapping between the 2D texture images and the 3D geometric model. For evaluation of texture registration with ground truth, accurate datasets can be obtained with a complex setup consisting of calibrated geometry and texture capture devices. We do not have any knowledge of such evaluation performed; current evaluations reflect, at their best, the precision achieved by the algorithms, but fail to identify a possible bias. We propose a new evaluation measure based on the epipolar geometry of texture image pairs, with the advantage that the ground truth can be extracted solely from the texture images, independent of the 3D acquisition. We developed a noise model suitable to our purpose and analysed three distance measures based on epipolar geometry, well known in the computer vision community, to find new theoretical and experimental results. Finally, using the proposed framework, we evaluated a texture registration algorithm based on mutual information and found that its accuracy was under half-pixel.