流线形风格化图像生成算法

流线形风格化图像是印象派风格的典型代表,其艺术特点是通过流线条表现狂野与活泼的流动感,又通过色彩的层叠感表现时空的凝滞性.提出一种流线形风格化图像绘制算法,通过提取目标图像的结构矢量场,利用欧拉弹性模型进行光顺化得到流线场;通过结合凹凸映射的多源光照渲染和色彩扰动得到色彩层叠感强的纹理图;然后利用线积分卷积方法对流线场和纹理图进行合成,并利用样本梵高图像进行颜色传输得到最终的绘制结果.实验结果表明该算法自动化程度高,绘制结果具有较好的流线流动感和色彩层叠感.     

运用流体模拟的油画生成方法

与真实感绘制技术关注于传统的3D图形学不同,非真实感绘制技术更加强调艺术表现力、主观意识与情绪的传递以及强化重要信息、忽略非关键信息等方面.提出了一种自动的、基于流体模拟的方法来生成具有凡高后期风格的油画图像.提出以流体线条参考图颜色梯度的法线方向作为画笔方向,对原图进行多层绘制;同时,提出一种改进的多光源局部光照模型,以有效地反映不同光照条件下艺术图像的不同表征力.另外,设计了一种在光照条件下模拟画笔物理特征的方法,该方法通过bump-mapping增强绘制图像的涂料层叠感.为了使生成的绘制图像具有凡高油画的色彩风格,采用了一种颜色转换方法,将特定的艺术原画色彩特征转换到绘制图像上.实验结果表明,对于给定的输入图像,该算法能够有效地生成具有凡高后期艺术风格的油画.     

一种基于NPR的虚拟环境生成方法

非真实感绘制(NPR)为传统虚拟现实技术的使用开辟了新的空间。针对传统基于图像的绘制无法满足艺术风格虚拟环境需要的问题,通过将非真实感绘制技术引入虚拟场景构建中,提出了一种基于非真实感绘制的虚拟环境生成方法。该方法首先通过计算结构张量刻画图像局部结构,并采用全变分偏微分方程自适应滤波处理来得到平滑张量场;然后在此基础上采用线积分卷积指导画笔走向来模拟生成线条波动感艺术图像;最后将其融入3维场景来生成可漫游的艺术感虚拟环境。实验结果表明,采用该新算法不仅可以较好地模拟线条波动感艺术图像,而且可实现艺术风格虚拟环境的构建。     

一种流体艺术风格的自适应LIC绘制方法

把LIC算法应用到非真实感绘制中,提出一种自适应流体艺术图的LIC绘制方法.对源图像亮度分量计算切矢量场,然后对其进行增强、平滑处理获得结构矢量场;通过随机扰动源图像获得纹理参考图像;根据结构矢量场和纹理参考图像的局部特征产生可变的LIC积分步长和步数,自适应地处理纹理参考图像;最后对绘制效果进行颜色渲染,生成具有丰富颜色特征的流体艺术图.实验表明,该方法能够较好地模拟诸如梵高画的流体艺术风格,呈现生动、灵活的波动感.     

偏离映射的烙画风格绘制

针对非真实感绘制烙画艺术风格模拟技术中可能存在的背景单一、绘制速度慢以及缺少细节及写意效果等问题,提出一种自动的、基于偏离映射的烙画风格绘制方法。算法采用对烙画的前景和背景图像分别处理再进行融合的方法,首先通过边界扩充、种子点填充、L2距离优化等改进的纹理合成算法,将样本合成为烙画背景图像,扩展了背景题材;其次,采用各向异性滤波平滑前景图像的结构张量场,并沿张量场局部曲线方向进行线积分卷积计算的方法突出了烙画前景写意风格的特点,同时通过图像增强技术增强了局部细节和结构信息。此外,采用改进的Phong光照明模型将前景图像偏离映射到背景图像中。最终的实验结果突出了细节信息和写意效果,增强了艺术表现力,提高了绘制速度,能模拟出真实的烙画艺术效果。     

铅笔画的自适应LIC绘制方法

提出一种非真实感铅笔画的绘制方法,通过对图像的亮度分量计算切矢量场,获得图像的结构矢量场。根据矢量场和图像分割后的局部特征产生可变的积分步数和纹理走势。利用线积分卷积方法,自适应地处理图像。将绘制结果和通过霓虹处理得到的轮廓效果相结合。实验结果表明,该方法能够根据图像的细节丰富情况模拟铅笔画的艺术风格,并且生成速度较快。     

粉笔画艺术风格模拟

目的 对不同艺术风格的模拟和绘制是非真实感绘制技术的主要任务之一,目前非真实感绘制技术已对油画、水彩画、中国书法等国内外艺术风格进行了模拟,然而对粉笔化艺术风格的模拟方法并不多见。本文提出了一种基于滤波扩散和线积分卷积（LIC）的粉笔画艺术风格绘制技术。方法 首先输入2维目标图像,通过对目标图像二值化处理、边缘提取操作,获得连续、光滑的边缘信息,并采用滤波扩散技术对边缘图像进行扩散处理,模拟粉笔画中笔划的毛糙效果,同时通过采用图像增强方法增强了笔划的细节信息;其次,由于真实粉笔画在创作时,粉笔颜料黏附在图像局部区域,形成具有方向的笔刷纹理效果,算法通过在目标图像中添加白噪声,基于线积分卷积LIC产生具有方向的粉笔画笔刷纹理,并通过形态学膨胀处理获得粉笔画的笔划纹理,模拟出粉笔画中笔划的笔触特征。再次,真实的粉笔画艺术效果往往在黑板、木材等材质中创作,算法将产生的笔刷纹理图像、色彩信息以及边缘图像通过图层映射方法,映射到黑板材质等输入背景图像中,产生最终的粉笔画艺术效果图像。结果 通过对输入2维图像进行实验,模拟出具有粉笔画艺术效果的结果图像,突出了粉笔画的线条细节信息和笔划艺术特征。结论 提出了一种粉笔画艺术效果模拟算法,非真实感绘制领域的有效补充,算法简单有效,能模拟出真实的粉笔画艺术效果,增强了艺术表现力。     

非真实感绘制漫画艺术效果的研究与实现

提出了一种基于非真实感绘制的漫画艺术效果绘制算法。算法首先将输入图像从 RGB 色彩空间转换为LAB 色彩空间,通过双边滤波及色彩量化的方法对输入图像进行处理,获 得连续的、局部区域色彩一致的结果图像,可通过权值等参数对滤波及量化程度进行控制。其次, 采用DOG 滤波器和阈值处理求取输入图像的边缘信息,获得连续的、清晰的边缘。最后将边缘 图像融合到量化结果图像中,获得最终的漫画艺术效果。从最终的漫画艺术绘制效果看出,该算 法简单、易于实现。     

基于特征流的抽象线条画绘制

为了将照片图像转换为具有一定艺术美感的线条画图像,文中设计了3种基于特征流的各向异性滤波器:FGsD滤波器、FGaD滤波器和FLSM滤波器.这些滤波器的主要任务是提取图像的边缘信息,并将其显示为光滑连续的风格化线条.前两种滤波器是在分析数字图像中基于一阶微分和二阶微分边缘检测算法的性能后,将高斯一阶导滤波结果和高斯差分滤波结果进行适当的混合作为边缘检测的微分响应,然后对混合的微分响应值进行柔和阈值化处理提取边缘点.第3种滤波器是专门针对图像中的线型边结构提出的,通过计算局部亮度相似度质量来判断该像素是否属于边缘点.如果将FGsD滤波结果和FLSM滤波结果进行叠加,还可以得到明暗对比度增强的抽象线条画效果.与已有的线条画绘制算法相比,采用文中算法所生成的线条画视觉特征更鲜明、风格化效果更突出、艺术表现力更强烈.     

一种基于笔刷的非真实感绘制算法的研究

非真实感绘制是计算机图形学的一个分支,基于笔刷的非真实感绘制是非真实感绘制的重要内容.给出一种基于笔刷的多重非真实感绘制算法.算法运用源图像灰度图像的颜色梯度法线方向作为笔刷的方向,以颜色空间距离来控制笔刷的绘制.实验结果表明,对于给定的输入图像,该算法能够有效地生成具有油画艺术风格的图像.     

基于线性八叉树的快速直接体绘制算法

提出了基于线性八叉树的加速体绘制算法.利用线性八叉树对物体进行空间剖分,光线投射法跨越体数据集中的空体素,以提高绘制的速度.针对光线穿越体数据时的特殊情况,改进线性八叉树邻域查找的方法,特别是不同尺寸的邻域查找方法,克服了层次八叉树邻域查找的低效率,同时提出了光线离开平面的简洁判定方法,方便光线下一个采样点的计算.实验结果表明,该算法能够有效地提高绘制的速度.     

真实感图形绘制技术研究

随着虚拟现实技术的发展,对各种图形绘制技术提出了越来越高的要求。好的图形绘制技术是虚拟现实、动态仿真、实时可视化、高品质动画等越来越多的图像、图形应用技术的实现基础。本文主要介绍了基于图像的绘制技术、基于点的绘制技术,以及基于图形与图像的混合绘制技术在原理和应用。     

Physically Based Real-Time Rendering of Teeth and Partial Restorations

Visually accurate real-time rendering of teeth has many applications ranging from computer games to dental computer aided design (CAD). Similar to skin, the realistic and physically correct appearance of teeth cannot be achieved by simply using opaque diffuse textures, mainly because of the subsurface scattering behaviours of both. While both have a layered structure in common, the scattering characteristics of the teeth layers are drastically different from those of the skin, making rendering much more complicated. We present an approach which uses the Henyey–Greenstein scattering to achieve a near realistic real-time rendering of human teeth. To simulate the multi-layered geometry of teeth, we use standardized teeth models with dentin cores and fit them to real scanned teeth or dental restorations. By using a proxy geometry to compute the scattering, we can also render partial restorations as they would look like when attached to the remaining teeth. Finally, we compare our results to the VITA shade systems and human teeth to evaluate the visual fidelity of our approach.     

A Semi-Procedural Convolutional Material Prior

Lightweight material capture methods require a material prior, defining the subspace of plausible textures within the large space of unconstrained texel grids. Previous work has either used deep neural networks (trained on large synthetic material datasets) or procedural node graphs (constructed by expert artists) as such priors. In this paper, we propose a semi-procedural differentiable material prior that represents materials as a set of (typically procedural) grayscale noises and patterns that are processed by a sequence of lightweight learnable convolutional filter operations. We demonstrate that the restricted structure of this architecture acts as an inductive bias on the space of material appearances, allowing us to optimize the weights of the convolutions per-material, with no need for pre-training on a large dataset. Combined with a differentiable rendering step and a perceptual loss, we enable single-image tileable material capture comparable with state of the art. Our approach does not target the pixel-perfect recovery of the material, but rather uses noises and patterns as input to match the target appearance. To achieve this, it does not require complex procedural graphs, and has a much lower complexity, computational cost and storage cost. We also enable control over the results, through changing the provided patterns and using guide maps to push the material properties towards a user-driven objective.     

Interactive Subsurface Scattering for Materials With High Scattering Distances

Existing algorithms for rendering subsurface scattering in real time cannot deal well with scattering over longer distances. Kernels for image space algorithms become very large in these circumstances and separation does not work anymore, while geometry-based algorithms cannot preserve details very well. We present a novel approach that deals with all these downsides. While for lower scattering distances, the advantages of geometry-based methods are small, this is not the case anymore for high scattering distances (as we will show). Our proposed method takes advantage of the highly detailed results of image space algorithms and combines it with a geometry-based method to add the essential scattering from sources not included in image space. Our algorithm does not require pre-computation based on the scene's geometry, it can be applied to static and animated objects directly. Our method is able to provide results that come close to ray-traced images which we will show in direct comparisons with images generated by PBRT. We will compare our results to state of the art techniques that are applicable in these scenarios and will show that we provide superior image quality while maintaining interactive rendering times.      

硬件支持下的实时毛发动画

长期以来，由于图形硬件提供的能力有限，毛发动画一直只能限制在非实时动画创作领域之中。现在，随着图形硬件技术的发展，特别是可编程图形硬件的出现，实时毛发动画技术已趋成熟，逐渐进入实用阶段。本文在回顾毛发动画技术发展历程的基础上，结合当前的图形硬件发展水平，从建模，渲染与动画三个方面分别论述了实现实时毛发动画的相关算法与技术。     

Decision trees for accelerating unimodal, hybrid and multimodal rendering models

This paper deals with the rendering of segmented unimodal, hybrid and aligned multimodal voxel models. We propose a data structure that classifies the segmented voxels into categories, so that whenever the model has to be traversed, only the selected categories are visited and the empty and non-selected voxels are skipped. This strategy is based on: (i) a decision tree, called the rendering decision tree (RDT), which represents the hierarchy of the classification process and (ii) an intermediate run-length encoding (RLE) of the classified voxel model. The traversal of the voxel model given a user query consists of two steps: first, the RDT is traversed and the set of selected categories computed; next, the RLE is visited, but the non-selected runs are skipped and only the voxels of the original model that are codified are accessed in selected runs of the RLE. This strategy has been used to render a voxel model by back-to-front traversal and splatting as well as to construct 3D textures for hardware-driven 3D texture mapping. The results show that the voxel model traversal is significantly accelerated.     

Real-Time Watercolor for Animation

We present algorithms that allow for real-time rendering of 3D-scenes with a watercolor painting appearance. Our approach provides an appropriate simplification of the visual complexity, imitates characteristic natural effects of watercolor, and provides two essential painting techniques: the wet-on-wet and the wet-on-dry painting. We concentrate on efficient algorithms based on image space processing rather than on an exact simulation. This allows for the real-time rendering of 3D-scenes. During an animation a high frame-to-frame coherence can be achieved due to a stable segmentation scheme. Finally, we seamlessly integrate a smooth illumination into the watercolor renderings using information from the 3D-scene.     

基于图像的铅笔画绘制技术的研究现状与展望

非真实感绘制(Non-Photorcalistic Rendcring,NPR)是计算机图形学领域的一个分支,旨在使用计算机来生成具有某种艺术效果的作品。目前,非真实感绘制技术已经能够成功地模拟油画、水彩画、卡通画、铅笔画等艺术风格,在许多领域得到很广泛的应用。铅笔素描是艺术造型的基础。作为一种最简单的艺术表现形式,铅笔画凭借其简洁流畅的特点深受广大艺术爱好者的喜爱。如今,基于图像的铅笔画绘制技术已经是NPR领域的一个重要组成部分,受到诸多研究人员的关注,但该技术仍处于成长阶段,算法的通用性还无法满足现实应用的需求。     

基于GPU的三维医学图像混合可视化系统

研究并实现了一个基于GPU的医学图像混合可视化系统，该系统采用三维纹理映射的方法实现直接体绘制，利用GPU的可编程特性完成体绘制方法中的插值后分类算法和传输函数的传递及实时修改，采用OpenGL技术实现表面的绘制，并基于场景图结构实现时表面数据的管理。面绘制和体绘制部分都采用OpenGL实现，运用OpenGL的融合机制，系统实现了面绘制和体绘制的混合显示。本系统大大提高了体绘制的速度，有效地保留了面绘制和体绘制的优势，在保证绘制速度的基础上丰富了图像信息。