GPU通用计算平台上的SPH流体模拟

针对流体模拟需要大量计算资源从而很难达到实时模拟的问题,提出一种完全在GPU上实现的基于平滑粒子流体动力学的流体模拟方法.首先通过在GPU上构造基于哈希函数的空间均匀网格来实现任意大小场景的快速邻近粒子查找,并在GPU上并行求解SPH流体方程来实现流体模拟;渲染流体时,通过在顶点着色器中进行纹理采样,利用粒子坐标缓存数据直接更新流体粒子系统的顶点缓存,从而避免了CPU—GPU之间的数据传输,充分利用了GPU的并行性.实验对比表明,与纯CPU实现以及CPU和GPU混合实现的模拟结果相比,采用该方法能显著地减少单个时间片的计算时间,大幅度提高流体模拟和渲染的整体性能.     

基于CUDA的大规模流体实时模拟

流体模拟是计算机图形学中一个重要课题。使用基于粒子的光滑流体动力学SPH(smoothed particle hydrodynamics)方法模拟大规模流体的运动需要大量的粒子模拟流体,计算量巨大,传统的方法很难达到实时性要求。为了解决该问题,使用NVIDIA的并行计算架构CUDA(Compute Unified Device Architecture)将SPH方法的全部处理过程在GPU上实现,充分利用了GPU并行计算的性能优势。使用Z-order排列改进已有的并行邻域搜索算法,并通过优化数据结构及存储器分配,有效缓解了SPH方法在GPU架构上的性能瓶颈。实验结果表明,该方法能实时逼真地模拟大规模流体,与已有的GPU方法相比处理速度有显著的提升。     

基于粒子的动态流体模拟与GPU实现

针对动态流体模拟的细节复杂特性，采用一种基于粒子的新方法，当流体发生大幅动态变化时，该方法在描述流体细节方面取得更好效果。在模拟实现方面，在GPU上采用并行处理，提高模拟速度，实现计算机动画的实时模拟。     

真实感火焰模拟

针对火焰的计算机模拟难以实现真实感和实时性的问题,提出一种基于物理模型与图形处理器(GPU)通用计算相结合的火焰模拟方法.该方法首先采用半拉格朗日法求解流体方程,运用基于3D纹理的体绘制对火焰进行三维渲染.然后,根据光照和密度场将光谱转换成颜色分布来模拟火焰颜色,并在GPU上加速实现,使得真实感和实时性之间达到了平衡.     

基于GPU的实时线绘制及水墨仿真研究

为了由简单三维输入自动生成水墨仿真风格图像,提出了一种基于GPU的实时线绘制算法及水墨仿真算法。提出的微分几何线绘制算法结合了视点相关和视点无关两类特征线的绘制,利用了多种曲率信息和风格化纹理。由于GPU加速和风格化纹理的设计,该算法达到实时且风格化可控,方便了国画仿真,仿真计算将水墨看作二维流体,利用LB方法模拟水墨在宣纸中的边缘扩散。通过对比大量的绘制结果以及和其他方法的比较,结果表明,该方法的绘制结果更加清晰逼真,绘制实时完成且完全自动化。     

基于GPU多纹理混合技术的循经感传模拟的设计与实现

为了在虚拟人体经络系统中模拟循经感传现象,提出了一种基于GPU的纹理混合技术,通过对三张不同色的纹理贴图进行采样,在GPU的像素着色器中根据混合公式合成最终的纹理,实现了循经感传动态模拟效果.程序设计结果表明:在不同的模拟参数下,系统都能够实时逼真地重现循经感传过程.因此采用多纹理混合技术来模拟感传是一个合理有效的解决方案.     

一个SPH流体实时模拟的全GPU实现框架

怎样实时地进行高度逼真的大规模流体模拟是图形学要研究的一个重要内容。流体的模拟由物理计算、碰撞检测、表面重构和渲染几个部分组成,因此有大量工作针对流体模拟中的各个部分算法进行GPU加速。提出一整套基于GPU的SPH流体模拟加速框架。在利用平滑粒子动力学(SPH)求解Navier-Stokes方程的基础上,借助基于GPU的空间划分PSS(Parallel Spatial Subdivision)来大幅度提升粒子碰撞的检测速度。同时,设计一种基于几何着色器(Geometry Shader)的流体表面信息的重建算法,并进一步地实现基于索引的优化,使得在流体表面重建过程无须遍历不包含表面的区域。实验结果表明,该方法能实时模拟出具有较好真实感的流体场景。     

可扩展的实时自然景物模拟算法

针对传统的粒子系统实时仿真存在只能针对单一自然景物模拟、计算耗时、图像不真实、算法复杂等问题,提出了一种基于粒子系统和图形处理器（GPU）加速通用可扩展的自然景物模拟算法。在该算法中,粒子的物理运动计算过程和渲染阶段完全由CPU转移至GPU,可以增加粒子数量和提高渲染速度;同时,在渲染过程中,可以较好地利用硬件支持的粒子图技术来改善渲染中粒子的外表,选择不同纹理,从而能够较方便地模拟不同的自然景物。最后,在GPU上实现了雪花、喷泉、烟花、瀑布等模拟,算法充分利用了GPU的多通道并行处理性和可编程性,提高了自然景物模拟的实时性,可运用于虚拟现实系统。     

基于GPU的八叉树结构纹理研究与应用

八叉树结构纹理的应用很好地解决了复杂模型表面2D纹理映射的不足,GPU的高速发展,为八叉树结构纹理在GPU上的现实提供了解决方案。本文将八叉树结构纹理编码为2D纹理,并以节点的广度优先遍历方式在GPU上进行存储,在片段程序访问时提出一种自顶向下的查找方法。实验证明,本文方法取得了准确的纹理映射效果并提高了效率。该方法可以应用于任何需要在复杂物体表面上存储信息的情况。     

GPU并行计算加速的实时可视外壳三维重建及其虚实交互

针对现有的基于图像的三维重建方法难以实现真实物体的快速三维重建,无法满足虚实交互等应用需求的问题,提出一种基于GPU并行计算的实时三维重建及其虚实交互方法.首先把物体所在空间剖分成具有数据独立性的体素集合,结合可视外壳重建算法和精确行进立方体算法并行遍历每个体素得到体素状态序列;然后并行压缩体素状态序列得到非空体素集合,对非空体素进行并行三角形网格化,并利用图形硬件的多重纹理映射和可编程功能进行基于像素的纹理映射;最后假定虚拟物体的粒子为运动受限的拉格朗日流体粒子,重建物体网格顶点为流体边界,通过流体动力学方程的并行光滑粒子动力学方法求解来计算虚实交互.实验结果表明,该方法在GPU上进行完全并行求解,在32×32×32的空间剖分精度下,实现了实时三维重建和20帧/s左右的虚实交互计算,适用于计算机图形学和虚拟现实等领域中的虚实交互应用.     

A model for real-time on-surface flows

Simulating fluid flows for visualization purposes is known to be one of the most challenging fields of the computer graphics domain. While rendering vast liquid areas has been widely addressed this last decade, few papers have tackled the problematic of on-surface flows, even though real-time applications such as drive simulators or video games could greatly benefit from such methods. We present a novel empirical method for the animation of liquid droplets lying on a flat surface, the core of our technique being a simulation operating on a 2D grid which is implementable on GPU. The wetted surface can freely be oriented in space and is not limited to translucent materials, the liquid flow being governed by external forces, the viscosity parameter and the presence of obstacles. Furthermore, we show how to simply incorporate in our simulation scheme two enriching visual effects, namely absorption and ink transport. Rendering can be achieved from an arbitrary view point using a GPU image based raycasting approach and takes into account the refraction and reflection of light. Even though our method doesn’t benefit from the literature of fluid mechanics, we show that convincing animations in terms of realism can be achieved in real-time.     

三维实时云建模与渲染在工业仿真中的应用

在云建模方面,提出一种基于物理仿真和艺术可控性相结合的方法,利用Navier-Stokes流体动力学公式描述单一云朵的聚散和运动,通过盒子的堆积来描述云朵的初始轮廓,最终在盒子内部按流体动力学规律填充粒子生成三维云模型.为了满足实时性要求,在可编程图形芯片上求解Navier-Stokes等式,以便利用图形芯片的并行处理能力加快求解速度.在云的实时渲染方面,基于太阳光照方向和天气状况提出了一种简单的光照模型,大幅度地提高了云的渲染速度.此外,还提出一种改进的环状Impostor技术来提高大范围云层的渲染速度,并通过Shader编程的方法解决了应用Impostor技术到Alpha融合场景中所出现的问题.基于所描述的理论模型,利用三维图形API开发了一套三维云仿真系统,并广泛应用于各种工业仿真和科技娱乐展示项目中,取得了较好的效果.利用该方法生成的云模型具有真实感强、渲染速度快等特点.     

Computer-Generated Marbling Textures: A GPU-Based Design System

A computer system for interactively creating marbling textures is built on the physical model of the traditional marbling process. The approach generates marbling designs as the result of color advection in the 2D flow fields obtained by numerically solving the Navier-Stokes equations on the GPU with a multigrid solver     

A real-time multigrid finite hexahedra method for elasticity simulation using CUDA

We present a multigrid approach for simulating elastic deformable objects in real time on recent NVIDIA GPU architectures. To accurately simulate large deformations we consider the co-rotated strain formulation. Our method is based on a finite element discretization of the deformable object using hexahedra. It draws upon recent work on multigrid schemes for the efficient numerical solution of partial differential equations on such discretizations. Due to the regular shape of the numerical stencil induced by the hexahedral regime, and since we use matrix-free formulations of all multigrid steps, computations and data layout can be restructured to avoid execution divergence of parallel running threads and to enable coalescing of memory accesses into single memory transactions. This enables to effectively exploit the GPU’s parallel processing units and high memory bandwidth via the CUDA parallel programming API. We demonstrate performance gains of up to a factor of 27 and 4 compared to a highly optimized CPU implementation on a single CPU core and 8 CPU cores, respectively. For hexahedral models consisting of as many as 269,000 elements our approach achieves physics-based simulation at 11 time steps per second.     

Vector graphics depicting marbling flow

We present an efficient framework for generating marbled textures that can be exported into a vector graphics format based on an explicit surface tracking method. The proposed method enables artists to create complex and realistic marbling textures that can be used for design purposes. Our algorithm is unique in that the marbling paint on the surface of water is represented as an enclosed contour and is advected by fluid flow to deform the marbling silhouette. In contrast to previous methods, in which the shape is tracked with a concentration density field in Eulerian grids, our approach facilitates greater complexity that is free from grid resolution and per-pixel computation while retaining real-time performance. To forestall the propagation of large vertices, we adaptively resample the contours, exploiting the curvature and the turbulence of the fluid as criteria. At the convection phase, we parallelly advect contour particles on a Graphics Processing Unit (GPU) in addition to applying volume corrections. Finally, we quickly remove extremely thin lines in shapes to remove dozens of vertices. We performed our method with an interactive prototype to demonstrate the robustness of the proposed method in several scenarios.     

Parallel computing of 3D smoking simulation based on OpenCL heterogeneous platform

Open Computing Language (OpenCL) is an open royalty-free standard for general purpose parallel programming across Central Processing Units (CPUs), Graphic Processing Units (GPUs) and other processors. This paper introduces OpenCL to implement real-time smoking simulation in a virtual surgery training simulation system. Firstly, the Computational Fluid Dynamics (CFD) is adopted to construct the real-time smoking simulation model based on the Navier?CStokes (N-S) equations of an incompressible fluid under the condition of normal temperature and pressure. Then we propose a parallel computing technique based on OpenCL to accomplish the parallel computing of smoking simulation model on CPU and GPU, respectively. Finally, we render the smoke in real time by using a three-dimensional (3D) texture volume rendering method. Experimental results show that the parallel computing technique we have proposed achieve a satisfactory effect on image quality and rendering rate both on CPU and GPU.     

基于流场的流动水体仿真

为了逼真地模拟自然河道中的流动水体,提出了一种基于流场的流动水体仿真方法.应用流体力学原理,实时计算稳定水流的速度,构建河流的流场,然后运用流场驱动并约束满足泊松碟分布的块状纹理在河道内移动,通过对块状纹理进行混合与渲染,构成了一种自然水体的动态流动效果.水面渲染采用GLSL (opengl shading language)着色器进行渲染,实际运用GPU可编程渲染管线进行图形计算,减少了CPU的实时运算量,提高程序的整体效率,实践表明,应用以上方法可以有效地模拟流域内的动态流动水体.     

Texture-based visualization of unsteady 3D flow by real-time advection and volumetric illumination

This paper presents an interactive technique for the dense texture-based visualization of unsteady 3D flow, taking into account issues of computational efficiency and visual perception. High efficiency is achieved by a 3D graphics processing unit (GPU)-based texture advection mechanism that implements logical 3D grid structures by physical memory in the form of 2D textures. This approach results in fast read and write access to physical memory, independent of GPU architecture. Slice-based direct volume rendering is used for the final display. We investigate two alternative methods for the volumetric illumination of the result of texture advection: First, gradient-based illumination that employs a real-time computation of gradients, and, second, line-based lighting based on illumination in codimension 2. In addition to the Phong model, perception-guided rendering methods are considered, such as cool/warm shading, halo rendering, or color-based depth cueing. The problems of clutter and occlusion are addressed by supporting a volumetric importance function that enhances features of the flow and reduces visual complexity in less interesting regions. GPU implementation aspects, performance measurements, and a discussion of results are included to demonstrate our visualization approach.     

基于CPU-GPU混合加速的SPH流体仿真方法

基于光滑粒子流体力学SPH的流体仿真是虚拟现实技术的重要研究内容,但SPH流体仿真需要大量的计算资源,采用一般计算方法难以实现流体仿真的实时性。流体仿真通常由物理计算、碰撞检测和渲染等部分组成,借助GPU并行加速粒子的物理属性计算和碰撞过程使SPH方法的实时流体仿真成为可能。为了满足流体仿真应用中的真实性和实时性需求,提出一种基于CPU GPU混合加速的SPH流体仿真方法,流体计算部分采用GPU并行加速,流体渲染部分采用基于CPU的OpenMP加速。实验结果表明,基于CPU GPU混合加速的SPH流体仿真方法与CPU实现相比,能显著地减少流体仿真单帧计算时间且能更快速地完成渲染任务。