公开(公告)号：US20100079452A1

公开(公告)日：2010-04-01

申请号：US12241046

申请日：2008-09-30

申请人： Kun Zhou ,  Hou Qiming ,  Baining Guo

发明人： Kun Zhou ,  Hou Qiming ,  Baining Guo

IPC分类号： G06T17/00 ,  G06T15/60

CPC分类号： G06T17/005 ,  G06F3/048 ,  G06T15/50

摘要： Described is a technology by which a GPU-based photon mapping mechanism/algorithm uses a kd-tree to render arbitrary dynamic scenes. For each frame, the mechanism emits and traces a set of photons into the scene. When a photon hits a surface, it can either be reflected, transmitted, or absorbed based on the surface material. Once photon tracing is done, a kd-tree is built for the stored photons. To estimate the radiance value at an arbitrary surface point, the k-nearest photons are located and filtered. The photon tracing and photon kd-tree construction, as well as the radiance estimation using k-nearest neighbor (KNN) searches are performed on graphics hardware, e.g., a GPU. In one example, only caustic photons are traced, whereby a photon is terminated and stored once it hits a diffuse surface.

摘要翻译： 描述了基于GPU的光子映射机制/算法使用kd-tree渲染任意动态场景的技术。 对于每个帧，机制发射并跟踪一组光子到场景中。 当光子撞击表面时，它可以根据表面材料进行反射，透射或吸收。 光子跟踪完成后，为存储的光子建立一个kd树。 为了估计任意表面点处的辐射值，定位和过滤k个最近的光子。 在图形硬件（例如GPU）上执行光子跟踪和光子kd-tree构造以及使用k-最近邻（KNN）搜索的辐射估计。 在一个示例中，仅追踪苛性光子，由此一旦光子撞击漫射表面，就终止并存储光子。

公开(公告)号：US20100033488A1

公开(公告)日：2010-02-11

申请号：US12189212

申请日：2008-08-11

申请人： Kun Zhou ,  Xiaohan Shi ,  Baining Guo

发明人： Kun Zhou ,  Xiaohan Shi ,  Baining Guo

IPC分类号： G06T15/70

CPC分类号： G06T13/40

摘要： An approach to enrich skeleton-driven animations with physically-based secondary deformation in real time is described. To achieve this goal, the technique described employs a surface-based deformable model that can interactively emulate the dynamics of both low- and high-frequency volumetric effects. Given a surface mesh and a few sample sequences of its physical behavior, a set of motion parameters of the material are learned during an off-line preprocessing step. The deformable model is then applicable to any given skeleton-driven animation of the surface mesh. Additionally, the described dynamic skinning technique can be entirely implemented on GPUs and executed with great efficiency. Thus, with minimal changes to the conventional graphics pipeline, the technique can drastically enhance the visual experience of skeleton-driven animations by adding secondary deformation in real time.

摘要翻译： 描述了一种以物理为基础的二次变形实时丰富骨架驱动动画的方法。 为了实现这一目标，所描述的技术采用基于表面的可变形模型，其可以交互地模拟低频和高频体积效应的动力学。 给定表面网格和其物理行为的几个样本序列，在离线预处理步骤期间学习材料的一组运动参数。 可变形模型然后适用于任何给定的骨架驱动的表面网格动画。 此外，所描述的动态外观技术可以完全在GPU上实现并且以高效率执行。 因此，通过对传统图形管线的最小改变，该技术可以通过实时添加二次变形来显着增强骨架驱动动画的视觉体验。

公开(公告)号：US20090244083A1

公开(公告)日：2009-10-01

申请号：US12059041

申请日：2008-03-31

申请人： Li-Yi Wei ,  Kun Zhou ,  Jianwei Han ,  Baining Guo ,  Heung-Yeung Shum

发明人： Li-Yi Wei ,  Kun Zhou ,  Jianwei Han ,  Baining Guo ,  Heung-Yeung Shum

IPC分类号： G09G5/00

CPC分类号： G06T11/001

摘要： A “texture generator” uses an inverse texture synthesis solution that runs in the opposite direction to traditional forward synthesis techniques to construct 2D texture compactions for use by a graphics processing unit (GPU) of a computer system. These small 2D texture compactions generally summarize an original globally variant texture or image, and are used to reconstruct the original texture or image, or to re-synthesize new textures or images under user-supplied constraints. In various embodiments, the texture generator uses the texture compaction to provide real-time synthesis of globally variant textures on a GPU, where texture memory is generally too small for large textures. Further, the texture generator provides an optimization framework for inverse texture synthesis which ensures that each input region is properly encoded in the output compaction. In addition, the texture generator also computes orientation fields for anisotropic textures containing both low- and high-frequency regions.

摘要翻译： “纹理生成器”使用逆向纹理合成解决方案，其以与传统的前向合成技术相反的方向运行，以构建2D纹理压缩以供计算机系统的图形处理单元（GPU）使用。 这些小的2D纹理压缩通常总结原始的全局变体纹理或图像，并用于重构原始纹理或图像，或者在用户提供的约束条件下重新合成新的纹理或图像。 在各种实施例中，纹理生成器使用纹理压缩以在GPU上提供全局变体纹理的实时合成，其中纹理存储器通常对于大纹理来说太小。 此外，纹理生成器提供用于逆纹理合成的优化框架，其确保每个输入区域在输出压缩中被适当地编码。 此外，纹理生成器还计算包含低频和高频区域的各向异性纹理的取向场。

公开(公告)号：US07538766B2

公开(公告)日：2009-05-26

申请号：US11147921

申请日：2005-06-08

申请人： Kun Zhou ,  Yaohua Hu ,  Stephen S. Lin ,  Baining Guo ,  Heung-Yeung Shum

发明人： Kun Zhou ,  Yaohua Hu ,  Stephen S. Lin ,  Baining Guo ,  Heung-Yeung Shum

IPC分类号： G06T15/00

CPC分类号： G06T15/60

摘要： Pre-computed shadow fields are described. In one aspect, shadow fields for multiple entities are pre-computed. The shadow fields are pre-computed independent of scene configuration. The multiple entities include at least one occluding object and at least one light source. A pre-computed shadow field for a light source indicates radiance from the light source. A pre-computed shadow field for an occluding object indicates occlusion of radiance from the at least one light source.

摘要翻译： 描述预先计算的阴影场。 在一个方面，多个实体的影子字段被预先计算。 阴影场是独立于场景配置预先计算的。 多个实体包括至少一个闭塞对象和至少一个光源。 用于光源的预计算阴影场指示来自光源的辐射。 用于闭塞物体的预计算阴影场表示遮挡来自至少一个光源的辐射。

公开(公告)号：US20090006051A1

公开(公告)日：2009-01-01

申请号：US11770942

申请日：2007-06-29

申请人： Kun Zhou ,  Qiming Hou ,  Minmin Gong ,  John Michael Snyder ,  Baining Guo ,  Heung-Yeung Shum

发明人： Kun Zhou ,  Qiming Hou ,  Minmin Gong ,  John Michael Snyder ,  Baining Guo ,  Heung-Yeung Shum

IPC分类号： G06G7/48

CPC分类号： G06T15/506

摘要： A real-time algorithm for rendering an inhomogeneous scattering medium such as fog is described. An input media animation is represented as a sequence of density fields, each of which is decomposed into a weighted sum of a set of radial basis functions (RBFs) such as Gaussians. The algorithm computes airlight and surface reflectance of the inhomogeneous scattering medium. Several approximations are taken which lead to analytical solutions of quantities such as an optical depth integrations and single scattering integrations, and a reduced number of integrations that need to be calculated. The resultant algorithm is able to render inhomogeneous media including their shadowing and scattering effects in real time. The algorithm may be adopted for a variety of light sources including point lights and environmental lights.

摘要翻译： 描述了用于渲染非均匀散射介质（如雾）的实时算法。 输入媒体动画被表示为密度字段的序列，每个密度字段被分解成一组径向基函数（RBF）如Gauss的加权和。 该算法计算不均匀散射介质的气孔和表面反射率。 采用几种近似方法，其导致诸如光学深度积分和单一散射积分的量的分析解，以及需要计算的减少的积分数。 所得到的算法能够实时渲染包括它们的阴影和散射效应的不均匀介质。 该算法可以用于各种光源，包括点光源和环境光源。

公开(公告)号：US20090006046A1

公开(公告)日：2009-01-01

申请号：US11830743

申请日：2007-07-30

申请人： Kun Zhou ,  Zhong Ren ,  Stephen Ssu-te Lin ,  Baining Guo ,  Heung-Yeung Shum

发明人： Kun Zhou ,  Zhong Ren ,  Stephen Ssu-te Lin ,  Baining Guo ,  Heung-Yeung Shum

IPC分类号： G06F17/10

CPC分类号： G06T15/55

摘要： A real-time algorithm for rendering of an inhomogeneous scattering media such as smoke under dynamic low-frequency environment lighting is described. An input media animation is represented as a sequence of density fields, each of which is represented by an approximate model density field and a residual density field. The algorithm uses the approximate model density field to compute an approximate source radiance, and further computes an effective exitant radiance by compositing the approximate source radiance using a compositing methods such as ray marching. During the compositing process (e.g., ray marching), the residual field is compensated back into the radiance integral to generate images of higher detail.

摘要翻译： 描述了在动态低频环境照明下渲染非均匀散射介质（如烟雾）的实时算法。 输入媒体动画被表示为密度域序列，每个密度场由近似模型密度场和残余密度域表示。 该算法使用近似模型密度场来计算近似辐射源，并且通过使用诸如射线行进之类的合成方法合成近似源辐射来进一步计算有效的出射辐射度。 在合成过程（例如，射线行进）期间，残余场被补偿回到辐射积分中以产生更高细节的图像。

公开(公告)号：US20090006044A1

公开(公告)日：2009-01-01

申请号：US11768894

申请日：2007-06-26

申请人： Kun Zhou ,  Zhong Ren ,  Stephen Ssu-te Lin ,  Baining Guo ,  Heung-Yeung Shum

发明人： Kun Zhou ,  Zhong Ren ,  Stephen Ssu-te Lin ,  Baining Guo ,  Heung-Yeung Shum

IPC分类号： G06F17/10

CPC分类号： G06T15/55

摘要： A real-time algorithm for rendering of an inhomogeneous scattering media such as smoke under dynamic low-frequency environment lighting is described. An input media animation is represented as a sequence of density fields, each of which is decompressed into a weighted sum of a set of radial basis functions (RBFs) and an optional residual field. Source radiances from single and optionally multiple scattering are directly computed at only the RBF centers and then approximated at other points in the volume using an RBF-based interpolation. Using the computed source radiances, a ray marching technique using slice-based integration of radiance along each viewing ray is performed to render the final image. During the ray marching process, the residual field may be compensated back into the radiance integral to generate images of higher detail.

摘要翻译： 描述了在动态低频环境照明下渲染非均匀散射介质（如烟雾）的实时算法。 输入媒体动画被表示为密度字段序列，每个密度字段被解压缩成一组径向基函数（RBF）和可选残余字段的加权和。 仅从RBF中心直接计算来自单个和任选多个散射的源辐射，然后使用基于RBF的插值在体积中的其他点处近似。 使用计算的源辐射，执行使用沿着每个观察射线的基于片段的辐射积分的射线行进技术来渲染最终图像。 在射线行进过程中，残余场可以被补偿回到辐射积分中以产生更高细节的图像。

公开(公告)号：US07286127B2

公开(公告)日：2007-10-23

申请号：US11158428

申请日：2005-06-22

申请人： Kun Zhou ,  John Michael Snyder ,  Xinguo Liu ,  Baining Guo ,  Heung-Yeung Shum

发明人： Kun Zhou ,  John Michael Snyder ,  Xinguo Liu ,  Baining Guo ,  Heung-Yeung Shum

IPC分类号： G06T15/00

CPC分类号： G06T17/20 ,  G06T13/20

摘要： Large mesh deformation using the volumetric graph Laplacian is described. In one aspect, information is received from a user, wherein the information indicates how an original mesh is to be deformed. The original mesh is then deformed based on the information and application of a volumetric differential operator to a volumetric graph generated from the original mesh.

摘要翻译： 描述了使用体积图拉普拉斯算子的大网格变形。 在一个方面，从用户接收信息，其中信息指示原始网格如何变形。 然后将原始网格基于体积差分算子的信息和应用变形为从原始网格生成的体积图。

公开(公告)号：US20060028481A1

公开(公告)日：2006-02-09

申请号：US11240878

申请日：2005-09-30

申请人： Jingdan Zhang ,  Kun Zhou ,  Baining Guo ,  Heung-Yeung Shum

发明人： Jingdan Zhang ,  Kun Zhou ,  Baining Guo ,  Heung-Yeung Shum

IPC分类号： G09G5/00

CPC分类号： G06T11/001

摘要： Methods for synthesizing progressively-variant textures based on texton masks are provided. A first method creates a synthesized texture image guided by a sample texture, first texton mask corresponding to the sample texture and a second texton mask modified based on the first texton mask. A second method also creates a synthesized texture image guided by a first and second sample textures and corresponding first and second texton masks. A method for rendering a synthesized texture on an image of a three-dimensional object includes creating a synthesized texture on the object guided by a two-dimensional progressively-variant sample texture, a texton mask for the sample texture and a mesh of a plurality of vertices representing the object.

公开(公告)号：US08963918B2

公开(公告)日：2015-02-24

申请号：US12241044

申请日：2008-09-30

申请人： Kun Zhou ,  Hou Qiming ,  Baining Guo

发明人： Kun Zhou ,  Hou Qiming ,  Baining Guo

IPC分类号： G06T15/00 ,  G06T15/06 ,  G06T17/00

CPC分类号： G06T15/06 ,  G06T17/005

摘要： Described is a technology by which a ray tracer incorporates a GPU-based kd-tree builder for rendering arbitrary dynamic scenes. For each frame, the ray tracer builds a kd-tree for the scene geometry. The ray tracer spawns and traces eye rays, reflective and refractive rays, and shadow rays. For each ray to be traced, the ray tracer walks through the kd-tree until it reaches leaf nodes and associated triangles. When a ray passes through both sides of a splitting plane, the “far” sub-tree is pushed into the stack and the “near” sub-tree is traversed first.

摘要翻译： 描述了一种技术，通过该技术，射线跟踪器结合了用于渲染任意动态场景的基于GPU的kd-tree构建器。 对于每个帧，光线跟踪器为场景几何构建一个kd-tree。 射线追踪器产生并追踪眼睛的光线，反射和折射光线以及阴影线。 对于要跟踪的每条光线，光线跟踪器穿过kd树，直到它到达叶节点和相关联的三角形。 当光线穿过分裂平面的两侧时，“远”子树被推入堆叠中，并且首先遍历“近”子树。