公开(公告)号：US06747651B1

公开(公告)日：2004-06-08

申请号：US09743921

申请日：2001-04-04

Applicant: Tiow Seng Tan ,  Ket Fah Chong ,  Kok Lim Low

Inventor： Tiow Seng Tan ,  Ket Fah Chong ,  Kok Lim Low

IPC: G06T1570

CPC classification number: G06T15/50 ,  G06T17/005

Abstract: This invention integrates model simplification and bounding volume hierarchy construction for collision detection in interactive 3D graphics. In particular, it provides general framework and a preferred method to construct bounding volume hierarchy using outputs of model simplification. Simplified models, besides their application to multi-resolution rendering, can provide clues to the shape of the input object. These clues help in the partitioning of the object's model into components that may be more tightly bounded by simple bounding volumes. The framework and method naturally employ both the bottom-up and the top-down approaches of hierarchy building, and thus can have the advantages of both approaches. The framework and method includes the steps of simplified models generation, component derivation, component tree generation, and bounding volume hierarchy generation. The operation of the method includes the steps of interactively computing, displaying and recording simplified models and bounding volume hierarchy in response to user commands. Ray tracing and collision detection may be efficiently performed using the bounding volume hierarchy generated by the invention.

Abstract translation: 本发明整合了交互式3D图形中的碰撞检测的模型简化和边界体积层次结构。 特别地，它提供了一般框架和使用模型简化的输出来构建边界体层次结构的优选方法。 简化的模型除了应用于多分辨率渲染之外，还可以为输入对象的形状提供线索。 这些线索有助于将对象的模型划分为可能由简单的边界卷更紧密地界定的组件。 框架和方法自然采用层次结构的自下而上和自上而下的方法，从而具有两种方法的优点。 框架和方法包括简化模型生成，组件导出，组件树生成和边界卷层次生成的步骤。 该方法的操作包括响应于用户命令交互地计算，显示和记录简化模型和界限体积层级的步骤。 可以使用由本发明生成的边界体积层次来有效地执行光线跟踪和碰撞检测。

公开(公告)号：US06710775B1

公开(公告)日：2004-03-23

申请号：US09595654

申请日：2000-06-16

Applicant: Joshua P. Tulman

Inventor： Joshua P. Tulman

IPC: G06T1570

CPC classification number: G06T15/20 ,  G06T13/80

Abstract: A method for producing an animation of an object includes displaying an object on a display of a computer system. A perspective system that has a predefined relationship with the object is created on the display. The perspective system defines different planes, and different portions of the object are associated with the different planes. Each of these different portions is stored as a different image file. The perspective system is rotated about the object to establish different frames of the animation. For each frame, the different portions of the object are manipulated to orient the object to establish the predefined relationship with the rotated perspective system. For each frame, script is created describing the manipulation of the different portions of the object.

Abstract translation: 用于产生对象的动画的方法包括在计算机系统的显示器上显示对象。 在显示器上创建与对象具有预定关系的透视系统。 透视系统定义不同的平面，并且对象的不同部分与不同的平面相关联。 这些不同部分中的每一个被存储为不同的图像文件。 透视系统围绕对象旋转以建立不同的动画框架。 对于每个帧，操纵对象的不同部分以使对象定向以与旋转的透视系统建立预定关系。 对于每个帧，创建描述对象的不同部分的操作的脚本。

公开(公告)号：US06664966B1

公开(公告)日：2003-12-16

申请号：US09662090

申请日：2000-09-14

Applicant: Peter Ibrahim ,  Christopher B. Lea ,  Adam D. Barr ,  Raymond Hill

Inventor： Peter Ibrahim ,  Christopher B. Lea ,  Adam D. Barr ,  Raymond Hill

IPC: G06T1570

CPC classification number: G11B27/34 ,  G11B27/034 ,  G11B2220/415

Abstract: A nonlinear editing system for audio, video and/or other source materials comprises a system to define at least one time line representing the edit, the time line being represented in the editing system as an operator graph. The operator graph includes operators, representing sources and time-based effects, and time varying connections therebetween. For each period of the defined time line wherein the connections do not change, a expression tree comprising a simplified representation of the operators and the connections required to render that portion of the time line is extracted. Each expression tree can be examined to ensure that all of the required sources and/or connections are available to render that portion of the time line in real time and, if this is not the case, a determination can be made of which portions of the expression tree can be pre-rendered to an intermediate result, the intermediate result being substituted into expression tree to provide real time rendering.

Abstract translation: 用于音频，视频和/或其他源材料的非线性编辑系统包括一个系统，用于定义表示编辑的至少一个时间线，该时间线在编辑系统中被表示为操作符图。 运算符图包括代表源和时间效应的运算符以及它们之间的时变连接。 对于其中连接不改变的所定义的时间线的每个周期，提取包括操作者的简化表示和呈现该时间线部分所需的连接的表达式树。 可以检查每个表达式树，以确保所有必需的源和/或连接可用于实时渲染时间线的部分，如果不是这样，则可以确定 表达式树可以预渲染为中间结果，将中间结果替换为表达式树以提供实时渲染。

公开(公告)号：US06646643B2

公开(公告)日：2003-11-11

申请号：US09755904

申请日：2001-01-05

Applicant: James N. Templeman

Inventor： James N. Templeman

IPC: G06T1570

CPC classification number: G06F3/012 ,  G06F3/011

Abstract: A method and apparatus for interfacing locomotive 3D movements of a user to a reference in a virtual or remote environment are provided. Initially, a 3D motion of a body portion of a user is sensed as the user takes a gestural pace. This sensing includes the determining of a beginning and an end of the gestural pace taken by the user, the determining of a 3D direction characteristic of the body portion motion during the gestural pace, and the determining of a 3D extent characteristic of the body portion motion during the gestural pace. Next, a 3D direction and extent of motion in the environment corresponding to the determined direction and extent characteristics of the gestural pace is computed. Finally, the computed 3D motion is used to move the reference in the environment.

公开(公告)号：US06646642B1

公开(公告)日：2003-11-11

申请号：US09663070

申请日：2000-09-14

Applicant: Katsuyuki Kanetaka ,  Toshio Fukui

Inventor： Katsuyuki Kanetaka ,  Toshio Fukui

IPC: G06T1570

CPC classification number: G06T13/20

Abstract: An image representing a motion of an object is obtained with a small processing volume. As shown in FIGS. 5A through 5G, positions in a three-dimensional space associated with sparks of a firework ball are sequentially calculated in accordance with motion characteristics of the sparks. Positions on a camera screen are obtained by projecting the calculated positions of the sparks at the current point in time in FIG. 5C, and a spark texture D is drawn in those positions. An image G representing a locus of each of the sparks is obtained by drawing a line segment connecting points that form a history of the points on the camera screen which are projections of points associated with each of the spark (points on a same radial line in FIG. 5F).

Abstract translation: 以小的处理量获得表示对象的运动的图像。 如图 如图5A至5G所示，根据火花的运动特性依次计算与火花球的火花有关的三维空间中的位置。 通过将计算出的火花位置投影在图1中的当前时间点来获得相机屏幕上的位置。 并且在这些位置绘制火花纹理D. 表示每个火花的轨迹的图像G通过绘制连接点的线段来获得，该线段形成相机屏幕上的点的历史，这些点是与每个火花相关联的点的投影（相同径向线上的点 图5F）。

公开(公告)号：US06633294B1

公开(公告)日：2003-10-14

申请号：US09802829

申请日：2001-03-09

Applicant: Seth Rosenthal ,  John R. Anderson ,  Steve Sullivan

Inventor： Seth Rosenthal ,  John R. Anderson ,  Steve Sullivan

IPC: G06T1570

CPC classification number: G06T13/40 ,  G06T7/20

Abstract: A technique for high-resolution motion capture according to the present invention includes a high-resolution makeup scheme and calibration object to optimize data capture. Data reduction and processing techniques reduce noise in the raw data and result in sufficient captured data to permit the use of several different image-processing techniques alone or in combination. The processed image data may be used to drive an animated character. It is emphasized that this abstract is provided to comply with the rules requiring an abstract that will allow a searcher or other reader to quickly ascertain the subject matter of the technical disclosure. It is submitted with the understanding that it will not be used to interpret or limit the scope or meaning of the claims.

Abstract translation: 根据本发明的用于高分辨率运动捕获的技术包括用于优化数据捕获的高分辨率补偿方案和校准对象。 数据简化和处理技术降低原始数据中的噪声，并产生足够的捕获数据，以允许单独或组合使用几种不同的图像处理技术。 经处理的图像数据可以用于驱动动画角色。 要强调的是，该摘要被提供以符合要求抽象的规则，允许搜索者或其他读者快速确定技术公开内容的主题。 提交它的理解是，它不会用于解释或限制权利要求的范围或含义。

公开(公告)号：US06611268B1

公开(公告)日：2003-08-26

申请号：US09643635

申请日：2000-08-22

Applicant: Richard S. Szeliski ,  David Salesin ,  Arno Schödl

Inventor： Richard S. Szeliski ,  David Salesin ,  Arno Schödl

IPC: G06T1570

CPC classification number: G06T13/80 ,  G06T7/194 ,  G06T7/215 ,  G06T2207/10021

Abstract: A system and process for generating a 3D video animation of an object referred to as a 3D Video Texture is presented. The 3D Video Texture is constructed by first simultaneously videotaping an object from two or more different cameras positioned at different locations. Video from, one of the cameras is used to extract, analyze and synthesize a video sprite of the object of interest. In addition, the first, contemporaneous, frames captured by at least two of the cameras are used to estimate a 3D depth map of the scene. The background of the scene contained within the depth map is then masked out, and a clear shot of the scene background taken before filming of the object began, leaving just the object. To generate each new frame in the 3D video animation, the extracted region making up a “frame” of the video sprite is mapped onto the previously generated 3D surface. The-resulting image is rendered from a novel viewpoint, and then combined with a flat image of the background which has been warped to the correct location. In cases where it is anticipated that the subject could move frequently, the foregoing part of the procedure associated with estimating a 3D depth map of the scene and extracting the 3D surface representation of the object is performed for each subsequent set of contemporaneous frames captured by at least two of the cameras.

Abstract translation: 提出了一种用于生成称为3D视频纹理的对象的3D视频动画的系统和过程。 3D视频纹理通过首先同时从位于不同位置的两个或更多个不同摄像机进行录像来构造。 其中一台相机用于提取，分析和综合感兴趣对象的视频精灵。 另外，使用由至少两个照相机拍摄的第一个同时代的帧来估计场景的3D深度图。 深度图中包含的场景的背景被遮蔽，并且在拍摄对象之前拍摄的场景背景的清晰镜头开始，仅留下对象。 为了在3D视频动画中生成每个新帧，构成视频精灵的“帧”的提取区域被映射到先前生成的3D表面上。 从新颖的角度渲染所得到的图像，然后与已经翘曲到正确位置的背景的平面图像组合。 在预期受试者可能频繁移动的情况下，与估计场景的3D深度图和提取对象的3D表面表示相关联的过程的前述部分对于每个随后的由下列组合捕获的同时期帧执行： 至少两台相机。

公开(公告)号：US06492990B1

公开(公告)日：2002-12-10

申请号：US09051417

申请日：1998-07-15

Applicant: Shmuel Peleg ,  Ran Cohen ,  David Avnir

Inventor： Shmuel Peleg ,  Ran Cohen ,  David Avnir

IPC: G06T1570

CPC classification number: G11B27/034 ,  G11B27/028 ,  G11B27/10 ,  H04N5/222 ,  H04N19/20 ,  Y10S345/949 ,  Y10S345/956 ,  Y10S345/957 ,  Y10S707/99942 ,  Y10S707/99943

Abstract: A method using computer software for automatic audio visual dubbing (5) using an efficient computerized automatic method for audio visual dubbing of movies by computerized image copying of the characteristic features of the lip movements of the dubber onto the mouth area of the original speaker. The invention uses a method of vicinity-searching, three-dimensional head modeling of the original speaker (3), and texture mapping (10) technique to produce new images which correspond to the dubbed sound track: The invention thus overcomes the well known disadvantage of the correlation problems between lip movement in an original movie and the sound track of the dubbed movie.

Abstract translation: 一种使用计算机软件进行自动音频视频复制的方法（5），使用有效的计算机化的自动化方法对电影进行音频视频配音，通过电脑化图像复制嘟嘟声的唇部运动的特征到原始扬声器的口部区域。 本发明使用原始扬声器（3）的近邻搜索，三维头部建模和纹理映射（10）技术来产生对应于配音声轨的新图像的方法：本发明克服了众所周知的缺点 原始电影中的嘴唇运动与被复制的电影的声轨之间的相关问题。

公开(公告)号：US06437808B1

公开(公告)日：2002-08-20

申请号：US09492582

申请日：2000-01-27

Applicant: Frank Z. Brill, III ,  Scott A. King

Inventor： Frank Z. Brill, III ,  Scott A. King

IPC: G06T1570

CPC classification number: G06T9/001 ,  G06T7/248 ,  G06T13/40 ,  G06T2207/10016 ,  G06T2207/30201 ,  H04N19/543

Abstract: An apparatus and method for transmitting graphical representations is disclosed. The present invention has an image generator (112) that generates an image (114) of a head (106) with facial features, including an eye portion (202) that correlates to an eye (240) in the head (106). The apparatus also has a non-updating tracker (116) that searches for an eye target image of the eye (240) in the head (106). The eye portion (202) correlating to the eye (240) is positioned at the target image located by the non-updating tracker (116). The apparatus also has an updating tracker (118) that searches for an updated eye target image when the non-updating tracker (116) is unable to locate the eye target image. The updating tracker (118) also positions the eye portion (202) at the updated eye target image and updates the updated eye target image with the eye portion (202). The updating tracker further determines the location of the eye portion (202). The apparatus also has an image differentiator (120) coupled to the trackers for providing image differential signals (124), including eye differential signals representing positional difference from the location of the eye portion (202). The apparatus also has a display device (130) that receives the image differential signals (124), including the eye differential signals, and animates a model (136) with the received image differential signals (134).

Abstract translation: 公开了用于发送图形表示的装置和方法。 本发明具有产生具有面部特征的头部（106）的图像（114）的图像生成器（112），其包括与头部（106）中的眼睛（240）相关联的眼睛部分（202）。 该装置还具有搜索头部（106）中的眼睛（240）的眼睛目标图像的非更新跟踪器（116）。 与眼睛（240）相关联的眼睛部分（202）位于由非更新跟踪器（116）定位的目标图像上。 当非更新跟踪器（116）不能定位眼睛目标图像时，该装置还具有搜索更新的眼睛目标图像的更新跟踪器（118）。 更新跟踪器（118）还将眼睛部分（202）定位在更新的眼睛目标图像上，并用眼睛部分（202）更新更新的眼睛目标图像。 更新跟踪器还确定眼睛部分（202）的位置。 该装置还具有耦合到跟踪器的图像微分器（120），用于提供图像差分信号（124），包括表示与眼睛部分（202）的位置的位置差异的眼睛差分信号。 该装置还具有接收包括眼睛差分信号的图像差分信号（124）并且利用接收到的图像差分信号（134）使模型（136）动画化的显示装置（130）。

公开(公告)号：US06437785B1

公开(公告)日：2002-08-20

申请号：US09303469

申请日：1999-04-30

Applicant: John J. Light ,  John D. Miller ,  Alan B. McConkie

Inventor： John J. Light ,  John D. Miller ,  Alan B. McConkie

IPC: G06T1570

CPC classification number: G06F3/0481

Abstract: Conveying a relationship between two objects in a scene is accomplished by selecting source and destination ends of an imaginary line between the objects in the scene, a source object being located at the source end, a destination object being located at the destination end. An image representing the destination object may be displayed near the source end of the imaginary line. The image may be animated to the location of the destination object along the imaginary line. A relationship indicator, such as a line, may also be displayed between the source object and the image as the image is animated to the destination end.

Abstract translation: 通过选择场景中的对象之间的假想线的源和目的地端点，源对象位于源端，目的地对象位于目的地端，来实现场景中两个对象之间的关系。 可以在虚拟源的源端附近显示表示目的地对象的图像。 图像可以沿着假想线被动画化为目标对象的位置。 当图像被动画化到目的地时，也可以在源对象和图像之间显示诸如行的关系指示符。