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：US07973798B2

公开(公告)日：2011-07-05

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：US08749543B2

公开(公告)日：2014-06-10

申请号：US11464721

申请日：2006-08-15

申请人： Jin Huang ,  Xiaohan Shi ,  Xinguo Liu ,  Kun Zhou ,  Li-Yi Wei ,  Baining Guo ,  Heung-Yeung Shum

发明人： Jin Huang ,  Xiaohan Shi ,  Xinguo Liu ,  Kun Zhou ,  Li-Yi Wei ,  Baining Guo ,  Heung-Yeung Shum

IPC分类号： G06T15/00 ,  G06T17/00 ,  G06T13/00 ,  G09G5/00

CPC分类号： G06T17/20 ,  G06T13/00

摘要： A computer implemented method for deforming a 3D polygon mesh using non-linear and linear constraints. The method includes creating a coarse control 3D polygon mesh that completely encapsulates the 3D polygon mesh to be deformed, projecting the deformation energy of the 3D polygon mesh and the constraints of the 3D polygon mesh to the vertices, or subspace, of the coarse control 3D polygon mesh, and determining the resulting deformed 3D polygon mesh by iteratively determining the deformation energy of the subspace. The constraints may be either linear or non-linear constraints, for example, a Laplacian constraint, a position constraint, a projection constraint, a skeleton constraint, or a volume constraint.

摘要翻译： 一种用于使用非线性和线性约束来变形3D多边形网格的计算机实现的方法。 该方法包括创建完全封装要变形的3D多边形网格的粗略控制3D多边形网格，将3D多边形网格的变形能量和3D多边形网格的约束投射到粗略控制3D的顶点或子空间 多边形网格，并且通过迭代地确定子空间的变形能量来确定产生的变形的3D多边形网格。 约束可以是线性或非线性约束，例如拉普拉斯约束，位置约束，投影约束，骨架约束或体积约束。

公开(公告)号：US08346002B2

公开(公告)日：2013-01-01

申请号：US11781227

申请日：2007-07-20

申请人： Li-Yi Wei ,  Kun Zhou ,  Baining Guo ,  Heung-Yeung Shum ,  Lvdi Wang

发明人： Li-Yi Wei ,  Kun Zhou ,  Baining Guo ,  Heung-Yeung Shum ,  Lvdi Wang

IPC分类号： G06K9/00

CPC分类号： G06T5/008

摘要： An apparatus and method provide for providing an output image from an input image. The input image may contain at least one portion that does not display certain desired information of the image, such as texture information. The desired information may be obtained from a second portion of the input image and applied to the at least one portion that does not contain the texture information or contains a diminished amount of the texture information. Also, at least one characteristic of the second portion of the input image may not be applied to the at least one portion such as illumination information. In another example, the input image may be decomposed into multiple parts such as a high frequency and a low frequency component. Each component may be hallucinated individually or independently and combined to form the output image.

摘要翻译： 一种设备和方法提供从输入图像提供输出图像。 输入图像可以包含不显示图像的某些所需信息的至少一个部分，例如纹理信息。 可以从输入图像的第二部分获得期望的信息，并将其应用于不包含纹理信息的至少一个部分或者包含纹理信息的减少量。 此外，输入图像的第二部分的至少一个特征可以不被应用于诸如照明信息的至少一个部分。 在另一示例中，输入图像可以被分解成多个部分，例如高频和低频分量。 每个组件可以单独地或独立地幻影，并组合以形成输出图像。

公开(公告)号：US20080043021A1

公开(公告)日：2008-02-21

申请号：US11464721

申请日：2006-08-15

申请人： Jin Huang ,  Xiaohan Shi ,  Xinguo Liu ,  Kun Zhou ,  Li-Yi Wei ,  Baining Guo ,  Heung-Yeung Shum

发明人： Jin Huang ,  Xiaohan Shi ,  Xinguo Liu ,  Kun Zhou ,  Li-Yi Wei ,  Baining Guo ,  Heung-Yeung Shum

IPC分类号： G09G5/00

CPC分类号： G06T17/20 ,  G06T13/00

摘要： A computer implemented method for deforming a 3D polygon mesh using non-linear and linear constraints. The method includes creating a coarse control 3D polygon mesh that completely encapsulates the 3D polygon mesh to be deformed, projecting the deformation energy of the 3D polygon mesh and the constraints of the 3D polygon mesh to the vertices, or subspace, of the coarse control 3D polygon mesh, and determining the resulting deformed 3D polygon mesh by iteratively determining the deformation energy of the subspace. The constraints may be either linear or non-linear constraints, for example, a Laplacian constraint, a position constraint, a projection constraint, a skeleton constraint, or a volume constraint.

摘要翻译： 一种用于使用非线性和线性约束来变形3D多边形网格的计算机实现的方法。 该方法包括创建完全封装要变形的3D多边形网格的粗略控制3D多边形网格，将3D多边形网格的变形能量和3D多边形网格的约束投射到粗略控制3D的顶点或子空间 多边形网格，并且通过迭代地确定子空间的变形能量来确定产生的变形的3D多边形网格。 约束可以是线性或非线性约束，例如拉普拉斯约束，位置约束，投影约束，骨架约束或体积约束。

公开(公告)号：US20090022414A1

公开(公告)日：2009-01-22

申请号：US11781227

申请日：2007-07-20

申请人： Li-Yi Wei ,  Kun Zhou ,  Baining Guo ,  Heung-Yeung Shum ,  Lvdi Wang

发明人： Li-Yi Wei ,  Kun Zhou ,  Baining Guo ,  Heung-Yeung Shum ,  Lvdi Wang

IPC分类号： G06K9/40

CPC分类号： G06T5/008

摘要： An apparatus and method provide for providing an output image from an input image. The input image may contain at least one portion that does not display certain desired information of the image, such as texture information. The desired information may be obtained from a second portion of the input image and applied to the at least one portion that does not contain the texture information or contains a diminished amount of the texture information. Also, at least one characteristic of the second portion of the input image may not be applied to the at least one portion such as illumination information. In another example, the input image may be decomposed into multiple parts such as a high frequency and a low frequency component. Each component may be hallucinated individually or independently and combined to form the output image.

摘要翻译： 一种设备和方法提供从输入图像提供输出图像。 输入图像可以包含不显示图像的某些所需信息的至少一个部分，例如纹理信息。 可以从输入图像的第二部分获得期望的信息，并将其应用于不包含纹理信息的至少一个部分或包含纹理信息的减少量。 此外，输入图像的第二部分的至少一个特征可以不被应用于诸如照明信息的至少一个部分。 在另一示例中，输入图像可以被分解成多个部分，例如高频和低频分量。 每个组件可以单独地或独立地幻影，并组合以形成输出图像。

公开(公告)号：US20090006052A1

公开(公告)日：2009-01-01

申请号：US11770974

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： G06T15/50

摘要： A real-time algorithm for rendering of an inhomogeneous scattering medium such as fog with a surface object immersed therein is described. An input media animation is represented as a sequence of density fields. The algorithm computes surface reflectance of the surface object in the inhomogeneous scattering medium. The algorithm may also compute airlight of the inhomogeneous scattering medium. Several approximations are taken which lead to analytical solutions of quantities such as 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 the 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（例如，其中浸入表面物体的雾）的实时算法。 输入媒体动画被表示为一系列密度字段。 该算法计算非均匀散射介质中表面物体的表面反射率。 该算法还可以计算不均匀散射介质的空气光。 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果的非均匀介质。 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：US07283140B2

公开(公告)日：2007-10-16

申请号：US11157657

申请日：2005-06-21

申请人： Kun Zhou ,  Xi Wang ,  Baining Guo ,  Heung-Yeung Shum

发明人： Kun Zhou ,  Xi Wang ,  Baining Guo ,  Heung-Yeung Shum

IPC分类号： G09G5/00 ,  G06K9/36 ,  G06T15/00 ,  G06T15/30

CPC分类号： G06T15/04

摘要： Texture montage is described. In one aspect, feature correspondences are received. The feature correspondences map at least one region on a 3-D mesh to at least one region on an image of one or more images. Each of the images provides texture information. An atlas of texture patches is created based on the feature correspondences. The atlas of texture patches provides for rendering texture from the images onto the 3-D mesh.

摘要翻译： 纹理蒙太奇被描述。 在一个方面，接收到特征对应。 特征对应将三维网格上的至少一个区域映射到一个或多个图像的图像上的至少一个区域。 每个图像提供纹理信息。 基于特征对应创建纹理补丁的图集。 纹理贴图的图集用于将图像中的纹理渲染到3-D网格上。

公开(公告)号：US20060284880A1

公开(公告)日：2006-12-21

申请号：US11157657

申请日：2005-06-21

申请人： Kun Zhou ,  Xi Wang ,  Baining Guo ,  Heung-Yeung Shum

发明人： Kun Zhou ,  Xi Wang ,  Baining Guo ,  Heung-Yeung Shum

IPC分类号： G09G5/00

CPC分类号： G06T15/04

摘要： Texture montage is described. In one aspect, feature correspondences are received. The feature correspondences map at least one region on a 3-D mesh to at least one region on an image of one or more images. Each of the images provides texture information. An atlas of texture patches is created based on the feature correspondences. The atlas of texture patches provides for rendering texture from the images onto the 3-D mesh.

摘要翻译： 纹理蒙太奇被描述。 在一个方面，接收到特征对应。 特征对应将三维网格上的至少一个区域映射到一个或多个图像的图像上的至少一个区域。 每个图像提供纹理信息。 基于特征对应创建纹理补丁的图集。 纹理贴图的图集用于将图像中的纹理渲染到3-D网格上。

公开(公告)号：US08190403B2

公开(公告)日：2012-05-29

申请号：US11830794

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 decomposed 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. Unique approximation techniques are introduced in the computational algorithms to simplify and speed up the computation of source radiance contributed by single and multiple scattering. Using the computed source radiances, a ray marching technique using slice-based integration of radiance along each viewing ray may be performed to render the final image.

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，每个密度字段被分解成一组径向基函数（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。 在计算算法中引入了独特的近似技术，以简化和加快由单次和多次散射贡献的源辐射的计算。 使用计算的源辐射，可以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。