Cutting and Pasting Irregularly Shaped Patches for Texture Synthesis

This paper proposes a patch‐based texture synthesis approach that cuts and stitches irregularly shaped texture patches to generate new texture images with minimized visual discontinuity. It works well on a wide range of textures. A semiautomatic algorithm is developed to obtain the irregularly shaped patches. To synthesize strictly structured textures, a regular pasting method is proposed to identify the texture structures and subsequently position the irregularly shaped patches according to the identified structures. The results and comparisons with related work are given.     

基于GPU加速的保结构纹理合成

提出一种基于Chamfer距离的保结构纹理合成方法。使用Chamfer距离度量纹理结构特征的相似度,在查找匹配块的同时计算纹理在颜色空间和结构特征空间的匹配度,从而解决以往纹理合成中有显著结构特征的纹理容易出现不连续的问题。但是Chamfer距离的计算量很大,而且随着纹理合成图分辨率的提高,计算成本会变得相当高昂以至于难以负担。因此,提出了基于GPU加速的保结构纹理合成方法,通过并行查找匹配块提高合成效率。实验证明本方法既提高了结构纹理的合成质量,又使得保结构纹理方法的合成速度大大提高,且与纹理合成图的分辨率无关。     

Texture synthesis via the matching compatibility between patches

A new patch-based texture synthesis method is presented in this paper. By the method, a set of patches that can be matched with a sampled patch for growing textures effectively, called the matching compatibility between patches, is generated first for each patch, and the set is further optimized by culling the patches that may cause synthesis conflicts. In this way, similarity measurement calculation for selecting suitable patches in texture synthesis can be greatly saved, and synthesis conflicts between neighbouring patches are substantially reduced. Furthermore, retrace computation is integrated in the synthesis process to improve the texture quality. As a result, the new method can produce high quality textures as texture optimization, the best method to date for producing good textures, and run in a time complexity linear to the size of the output texture. Experimental results show that the new method can interactively generate a large texture in 1024 × 1024 pixels, which is very difficult to achieve by existing methods. Supported by the National Basic Research Program of China (Grant No. 2009CB320802), the National Natural Science Foundation of China (Grant Nos. 60773026, 60833007), the National High-Tech Research & Development Program of China (Grant Nos. 2006AA01Z306, 2008AA01Z301), and the Research Grant of University of Macau     

Method of Direct Texture Synthesis on Arbitrary Surfaces

A direct texture synthesis method on arbitrary surfaces is proposed in this paper. The idea is to recursively map triangles on surface to texture space until the surface is completely mapped. First, the surface is simplified and a tangential vector field is created over the simplified mesh. Then, mapping process searches for the most optimal texture coordinates in texture sample for each triangle, and the textures of neighboring triangles are blended on the mesh. All synthesized texture triangles are compressed to an atlas. Finally, the simplified mesh is subdivided to approach the initial surface. The algorithm has several advantages over former methods: it synthesizes texture on surface without local parameterization; it does not need partitioning surface to patches; and it does not need a particular texture sample. The results demonstrate that the new algorithm is applicable to a wide variety of texture samples and any triangulated surfaces.     

多种子快速纹理合成

为避免纹理映射引起的接缝和扭曲,近几年人们提出了一些纹理合成方法。但大多数只能处理部分纹理,而且相当费时,为此,提出一种新的纹理合成算法,该算法在样图中选取多个种子,并将其预置到合成图中作为实始匹配点,然后通过螺旋状路径,在初始匹配点领域搜索寻找新匹配点进行合成,以此循环,直至合成图充满为止,该方法大大加快了合成速度,与穷尽搜索法相比,合成速度平均可以提高360倍,特别是在亮度空间合成时,在合成图象质量与RGB空间结果基本相同的情况下,可以实现进一步加速,另外,该算法还可合成沿方向变化的纹理,对不同纹理进行合成实验,其结果令人满意。     

在点模型上实现三维纹理合成的算法

为了避免网格重建过程而直接在三维点采样表面上进行纹理合成,研究了在点模型上的三维纹理合成的算法。利用KDtree这种数据结构在离散采样点上构建点与点的邻域关系,通过投影和建立匹配窗得到每一个待合成纹理的点与样图的映射关系,根据映射关系在样图中找出与待定点纹理值最佳匹配的点。最后将该匹配点的纹理值赋给待定点,同时结合邻域关系实现多点同时赋值。实验结果表明,该算法能有效地保持了生成的纹理结构和视觉效果的连续性和平滑性,具有耗时短、灵活可控、较好的鲁棒性等特点。     

基于泊松填充的纹理自适应插值方法

针对新图形技术条件下的纹理合成问题,提出一种纹理插值方法,可将源纹理图像自适应拉伸为不同尺寸的纹理图像并保持其清晰度不改变。首先,采用高维图像插值算法将源纹理裂变为目标纹理分辨率,作为中间过渡纹理;其次,利用自然图像的自相似性,依据中间纹理像素特征随机从源纹理中选取像素块;最后,使用泊松图像编辑算法将源纹理像素块平滑嵌入到中间纹理的间隙区域,得到最终的合成纹理。通过与现有算法的大量对比实验表明,该算法对静态和非静态纹理合成问题都能适用,且合成结果与源纹理具有较高的视觉一致性。另外,该算法逻辑简单、计算快速,无法复杂优化计算或者学习训练步骤,适合在低硬件配置的移动平台应用。     

基于PSO的Wang Tiles纹理合成

如何在纹理样图中选择组成Wang Tiles的图像块决定着纹理的合成质量。基于PSO的Wang Tiles纹理合成通过粒子群优化算法在纹理样图中快速搜索边界差异最小的图像块,并用选取的图像块构建Wang Tiles,最后用Wang Tiles纹理合成算法合成纹理。实验表明,该算法合成的纹理具有较少的接缝,比随机选择图像块具有更好的合成效果。     

纹理合成的自相关性判别法及其应用

从加快纹理相似性的判别速度出发,提出了一种纹理合成的自相关性判别法.传统的纹理合成算法随着邻域和样本的增大,计算量将成倍增加,纹理合成速度减慢的劣势逐渐体现出来.因此,算法对样本纹理建立简单的自相关性距离查找表,利用L邻域内像素的自相关性距离作为像素匹配的判别依据,以查找取代传统匹配过程中的繁琐计算,极大地加快了合成速度,可实现动态的、多精度的合成效果调控,以及避免块匹配中易出现纹理接缝的问题.经验证,该算法可在纹理合成、图像修补及纹理检索中应用,并可很好地达到实时的应用要求.     

面向纹理合成的块尺寸自动选择算法

在现有的基于块的纹理合成算法中,针对块尺寸需要人工选择从而导致纹理合成质量不确定的问题,提出一种纹理合成中的块尺寸自动选择算法。在纹理样本上按扫描线顺序滑动子块直到遍历所有位置,对子块与纹理样本的直方图进行归一化与均值滤波预处理,然后计算二者直方图的交;在不同子块位置的上述计算结果中,取其最大值作为子块与样本的颜色相似度。针对颜色相似度与块尺寸的近似单调递增关系,采用二分法计算相似度阈值点所对应的横坐标,将其作为纹理合成的块尺寸。多种类型纹理的实验结果表明,该方法自动选择的块尺寸与最佳经验取值范围相吻合。所提方法不仅适用于结构性纹理的合成,而且适用于随机性纹理的合成,能够获得理想的合成结果。     

点模型曲面的调和映射参数化

利用调和映射的平面和球面中值性质，提出了确定点模型曲面参数化映射中有关权因子的两种新方法，设计了能够达到内在变形较小的相应参数化方法，并将参数化方法应用于点模型曲面上的纹理映射．实验和统计结果表明，文中方法是比较有效的点模型曲面的参数化方法．     

采用邻域直方图匹配的矢量纹理图案合成

矢量纹理图案是指由一种或几种矢量图案元素按照一定的规则进行分布而形成的纹理图案。这种纹理图案在日常生活中随处可见,对其进行自动合成是非真实感绘制中的一个重要研究课题。本文提出一种基于样本的矢量纹理图案合成方法,可以根据一小块样本图案自动合成与该样本图案有类似分布规则的大面积图案。在此方法中,我们采用一种“邻域直方图”的策略来进行元素邻域信息的匹配与合成：将矢量元素的邻域空间用以该元素为中心的射线束和同心圆簇划分为一定数量的小格;统计每个小格中出现的邻域元素数量就可以形成一幅直方图;以此直方图信息作为当前元素的邻域信息在样本图案中进行匹配搜索,从而完成图案的合成。该方法不仅可以应用于仅有一种图案元素的分布合成,还可扩展至多种元素图案的复杂分布合成。与以往的矢量纹理图案合成方法相比,本文方法不需要复杂的元素关系分析和频繁的元素位置比较,实现简单,效率较高。实验表明,本文方法对于规则、半规则及随机的图案分布,都可达到较好的合成效果,这对于非真实感绘制中的风格图案生成、笔划分布计算等都将具有很好的应用意义。     

基于网格优化的图像纹理替换方法

提出一种新的图像纹理替换方法,该方法在原始图像精确几何及光照信息未知的情况下,用新的纹理有效替换原始图像目标区域的纹理并逼真地保持了原始纹理的扭曲变形和光照效果.该方法借助反求的法向信息,通过一种基于网格边长伸展的参数化方法优化求得原始图像目标区域上划分的网格在纹理空间中的对应网格,有效模拟了原始纹理由于隐藏几何和透视投影引起的纹理扭曲效果;进而通过YCbCr颜色空间转换和传递保持了原始纹理的光照阴影效果.由于求取纹理采样规则的优化方法仅仅与原始图像空间相关,而与替换纹理无关,因而对目标图像处理一次后,可以有效地应用于任意新纹理的替换.通过适当的交互,替换纹理的纹元尺度渐变及纹理自遮挡效果亦可有效模拟.实验展示了良好的纹理替换效果.     

Synthesis of Color Textures for Multimedia Applications

An algorithm for synthesizing color textures from a small set of parameters is presented in this paper. The synthesis algorithm is based on the 2-D moving average model, and realistic textures resembling many real textures can be synthesized using this algorithm. A maximum likelihood estimation algorithm to estimate parameters from a sample texture is also presented. By combining the estimation and synthesis algorithms, a color texture can be synthesized from a sample texture without human intervention. Using the estimated parameters, a texture larger than the original image can be synthesized from a small texture sample. The synthesis algorithm does not require an expensive iterative algorithm, and the quality of synthesized textures may be acceptable for many multimedia applications. In the experiment, various textures suitable for multimedia applications are synthesized from parameters estimated from real textures.     

复用计算的虚拟肝脏体纹理合成与映射方法

虚拟手术中器官纹理能够给用户直观反映,加强临场感和操作感。研究在虚拟肝脏手术中纹理的表现技术,先合成体纹理空间,把二维情况下基于复用计算的纹理合成技术进行改进,扩展至三维空间中进行体纹理块分布并着色;同时计算每个三角面片内部点集并着色,以此增加纹理的真实感;切割肝脏体能看到内部纹理。实验结果表明,该方法能够生成具有高度真实感以及同样本体纹理相似的三维纹理,且合成速度能够满足虚拟手术要求。     

纹理分布分析的快速图像修复算法

目前基于样本块的图像修复算法均是运用平方差和(SSD)准则遍历固定的样本集以选取最优匹配块,算法普遍具有运算效率低的缺点。针对现有算法进行改进,提出一种基于图像纹理分布分析的快速图像修复算法,该算法根据局部纹理变化动态确定样本集大小,解决样本集过大时引起的计算时间浪费以及样本集过小时样本多样性不足的问题。实验结果证明,该算法保证修复结果连续且符合人眼视觉要求,大大提高了图像修复的效率,具有实际意义。     

融合颜色和CS-LBP纹理的运动阴影检测

针对现存阴影检测方法存在的实时性和精确性兼顾不周的问题, 提出加权融合颜色和纹理特征的阴影检测方法: 首先利用HSV颜色信息提取疑似阴影点; 其次, 通过阴影的亮度比计算阴影亮度隶属度, 对于高亮度隶属度的疑似阴影点, 直接判定为阴影点, 减少了纹理检测的计算量; 然后对低亮度隶属度的疑似阴影点提取高效的CS-LBP纹理, 并进行纹理匹配, 根据纹理的相似程度及阴影空间分布特点, 计算出纹理隶属度; 最后, 根据实际中纹理随亮度变化的特点, 提出了依据亮度比自适应调整纹理隶属度权重的特征融合方法, 进行有效的阴影检测. 实验表明, 本文方法实时性良好, 可去除自阴影, 分割精度较佳, 隶属度方法的使用, 使本方法对光照变化及噪声更具有鲁棒性.     

A Randomized Approach for Patch-based Texture Synthesis using Wavelets

We present a wavelet‐based approach for selecting patches in patch‐based texture synthesis. We randomly select the first block that satisfies a minimum error criterion, computed from the wavelet coefficients (using 1D or 2D wavelets) for the overlapping region. We show that our wavelet‐based approach improves texture synthesis for samples where previous work fails, mainly textures with prominent aligned features. Also, it generates similar quality textures when compared against texture synthesis using feature maps with the advantage that our proposed method uses implicit edge information (since it is embedded in the wavelet coefficients) whereas feature maps rely explicitly on edge features. In previous work, the best patches are selected among all possible using a L2 norm on the RGB or grayscale pixel values of boundary zones. The L2 metric provides the raw pixel‐to‐pixel difference, disregarding relevant image structures — such as edges — that are relevant in the human visual system and therefore on synthesis of new textures.     

Self Tuning Texture Optimization

The goal of example‐based texture synthesis methods is to generate arbitrarily large textures from limited exemplars in order to fit the exact dimensions and resolution required for a specific modeling task. The challenge is to faithfully capture all of the visual characteristics of the exemplar texture, without introducing obvious repetitions or unnatural looking visual elements. While existing non‐parametric synthesis methods have made remarkable progress towards this goal, most such methods have been demonstrated only on relatively low‐resolution exemplars. Real‐world high resolution textures often contain texture details at multiple scales, which these methods have difficulty reproducing faithfully. In this work, we present a new general‐purpose and fully automatic self‐tuning non‐parametric texture synthesis method that extends Texture Optimization by introducing several key improvements that result in superior synthesis ability. Our method is able to self‐tune its various parameters and weights and focuses on addressing three challenging aspects of texture synthesis: (i) irregular large scale structures are faithfully reproduced through the use of automatically generated and weighted guidance channels; (ii) repetition and smoothing of texture patches is avoided by new spatial uniformity constraints; (iii) a smart initialization strategy is used in order to improve the synthesis of regular and near‐regular textures, without affecting textures that do not exhibit regularities. We demonstrate the versatility and robustness of our completely automatic approach on a variety of challenging high‐resolution texture exemplars.     

Texture Particles

This paper presents an analytical extension of texture synthesis techniques based on the distribution of elementary texture components. Our approach is similar to the bombing, cellular, macrostructured and lapped textures techniques, but provides the user with more control on both the texture analysis and synthesis phases. Therefore, high quality results can be obtained for a large number of structured or stochastic textures (bricks, marble, lawn, etc.). The analysis consists in decomposing textures into elementary components — that we call ``texture particles'' — and for which we analyze their specific spatial arrangements. The synthesis then consists in recomposing similar textures directly on arbitrary surfaces by taking into account the previously computed arrangements, extended to 3D surfaces. Compared to ``pixel‐based'' analysis and synthesis methods, which have been recently generalized to arbitrary surfaces, our approach has three major advantages: (1) it is fast, which allows the user to interactively control the synthesis process. This further allows us to propose a large number of tools, granting a high degree of artistic freedom to the user. (2) It avoids the visual deterioration of the texture components by preserving their shapes as well as their spatial arrangements. (3) The texture particles can be not only images, but also 3D geometric elements, which extends significantly the domain of application.