公开(公告)号：US07358978B2

公开(公告)日：2008-04-15

申请号：US10918840

申请日：2004-08-13

申请人： Baining Guo ,  Bo Zhang ,  Heung-Yeung Shum ,  Ligang Liu

发明人： Baining Guo ,  Bo Zhang ,  Heung-Yeung Shum ,  Ligang Liu

IPC分类号： G09G5/00

CPC分类号： G06T13/80 ,  G06T2210/44

摘要： An approach for morphing between planar shapes is disclosed. Correspondences are established between perceptual feature points that are extracted from both source and target shapes. A similarity metric between two feature points is defined using the intrinsic properties of their local neighborhoods. The optimal correspondence is found by an efficient dynamic programming technique. This approach treats shape noise by allowing the discarding of small feature points, which introduces skips in the traversal of the dynamic programming graph. Intermediate shapes are obtained by interpolating the overall shapes constructed by feature points and the detailed information of the shapes respectively.

摘要翻译： 公开了一种在平面形状之间变形的方法。 在从源和目标形状提取的知觉特征点之间建立对应关系。 两个特征点之间的相似性度量使用其本地邻域的固有属性来定义。 通过有效的动态规划技术找到最佳对应关系。 这种方法通过允许丢弃小特征点来处理形状噪声，这引起了遍历动态规划图的跳跃。 通过内插由特征点构成的整体形状和形状的详细信息来获得中间形状。

公开(公告)号：US07317843B2

公开(公告)日：2008-01-08

申请号：US10817633

申请日：2004-04-01

申请人： Jian Sun ,  Jiaya Jia ,  Heung-Yeung Shum

发明人： Jian Sun ,  Jiaya Jia ,  Heung-Yeung Shum

IPC分类号： G06K9/40 ,  G06K9/00

CPC分类号： G06T5/40 ,  G06T5/009 ,  G06T5/50 ,  G06T2207/10024 ,  G06T2207/10144 ,  H04N5/217 ,  H04N5/23229 ,  H04N5/2355 ,  H04N5/35581

摘要： Techniques are disclosed to improve quality of images that may be blurred or underexposed. In one described implementation, a method includes providing two images of a same scene. The method determines a spatial coherence and color statistics of the two images. The determined color statistics and spatial coherence are utilized to enhance one of the two images.

摘要翻译： 公开了提高可能模糊或曝光不足的图像质量的技术。 在一个描述的实现中，一种方法包括提供相同场景的两个图像。 该方法确定两个图像的空间相干性和颜色统计。 使用确定的颜色统计和空间相干性来增强两个图像之一。

公开(公告)号：US20070297646A1

公开(公告)日：2007-12-27

申请号：US11679275

申请日：2007-02-27

申请人： Lifeng Wang ,  Xi Wang ,  Xing Tong ,  Baining Guo ,  Heung-Yeung Shum

发明人： Lifeng Wang ,  Xi Wang ,  Xing Tong ,  Baining Guo ,  Heung-Yeung Shum

IPC分类号： G06K9/00

CPC分类号： G06T15/04

摘要： A computer implemented method for generating a representation of structure for use in rendering a synthesized image is provided. The representation is a view-dependent displacement mapping that represents displacements along a viewing direction. This view dependency allows the representation to be used to determine self shadows as well as shading, occlusion and silhouettes when used during rendering for synthesis.

摘要翻译： 提供了一种用于生成用于渲染合成图像的结构的表示的计算机实现的方法。 该表示是视图相关的位移映射，其表示沿观察方向的位移。 该视图依赖性允许在用于合成的渲染期间使用表示来确定自身阴影以及阴影，遮挡和剪影。

公开(公告)号：US07312797B2

公开(公告)日：2007-12-25

申请号：US11166559

申请日：2005-06-24

申请人： Xin Tong ,  Jiaping Wang ,  Stephen S. Lin ,  Baining Guo ,  Heung-Yeung Shum

发明人： Xin Tong ,  Jiaping Wang ,  Stephen S. Lin ,  Baining Guo ,  Heung-Yeung Shum

IPC分类号： G06T11/00

CPC分类号： G06T11/001 ,  G01N21/4795 ,  G06T15/506

摘要： Representing quasi-homogenous materials is described. In one aspect, quasi-homogenous materials are modeled to generate a material model of a physical sample. The material model identifies how light is scattered by the quasi-homogenous materials. The material model, independent of an object model of the physical sample, provides information that is useful to texture surfaces of arbitrary types and sizes of mesh models (e.g., representing the physical sample or other objects) with the quasi-homogenous materials.

摘要翻译： 描述了准均匀材料。 在一个方面，准均质材料被建模以产生物理样品的材料模型。 材料模型通过准均质材料识别光如何散射。 材料模型独立于物理样本的对象模型，提供了有用于使用准均质材料对任意类型和大小的网格模型（例如，表示物理样本或其他对象）的表面进行纹理的信息。

公开(公告)号：US20070133880A1

公开(公告)日：2007-06-14

申请号：US11469371

申请日：2006-08-31

申请人： Jian Sun ,  Heung-Yeung Shum ,  Xiaoou Tang ,  Weiwei Zhang

发明人： Jian Sun ,  Heung-Yeung Shum ,  Xiaoou Tang ,  Weiwei Zhang

IPC分类号： G06K9/46

CPC分类号： G06K9/38 ,  G06T7/11 ,  G06T7/90 ,  G06T2207/10016

摘要： Exemplary systems and methods segment a foreground from a background image in a video sequence. In one implementation, a system refines a segmentation boundary between the foreground and the background image by attenuating background contrast while preserving contrast of the segmentation boundary itself, providing an accurate background cut of live video in real time. A substitute background may then be merged with the segmented foreground within the live video. The system can apply an adaptive background color mixture model to improve segmentation of foreground from background under various background changes, such as camera movement, illumination change, and movement of small objects in the background.

摘要翻译： 示例性系统和方法从视频序列中的背景图像分割前景。 在一个实现中，系统通过衰减背景对比度同时保留分割边界本身的对比度来优化前景和背景图像之间的分割边界，从而实时提供实况视频的精确背景截图。 然后可以将替代背景与实时视频中的分段前景合并。 该系统可以应用自适应背景颜色混合模型，从而在各种背景变化（例如相机移动，照明变化和背景中的小物体的移动）下改进背景的前景分割。

公开(公告)号：US20070122028A1

公开(公告)日：2007-05-31

申请号：US11289907

申请日：2005-11-30

申请人： Jian Sun ,  Yin Li ,  Sing Kang ,  Heung-Yeung Shum

发明人： Jian Sun ,  Yin Li ,  Sing Kang ,  Heung-Yeung Shum

IPC分类号： G06K9/00

CPC分类号： G06K9/32

摘要： The present symmetric stereo matching technique provides a method for iteratively estimating a minimum energy for occlusion and disparity using belief propagation. The minimum energy is based on an energy minimization framework in which a visibility constraint is embedded. By embedding the visibility constraint, the present symmetric stereo matching technique treats both images equally, instead of treating one as a reference image. The visibility constraint ensures that occlusion in one view and the disparity in another view are consistent.

摘要翻译： 本对称立体匹配技术提供了一种使用置信传播迭代估计遮挡和视差的最小能量的方法。 最小能量基于嵌入可见性约束的能量最小化框架。 通过嵌入可见度约束，本对称立体匹配技术可以平等对待两个图像，而不是将其视为参考图像。 可见性约束确保一个视图中的遮挡和另一个视图中的视差是一致的。

公开(公告)号：US07196711B2

公开(公告)日：2007-03-27

申请号：US10698909

申请日：2003-10-31

申请人： Lifeng Wang ,  Xi Wang ,  Xin Tong ,  Baining Guo ,  Heung-Yeung Shum

发明人： Lifeng Wang ,  Xi Wang ,  Xin Tong ,  Baining Guo ,  Heung-Yeung Shum

IPC分类号： G09G5/00

CPC分类号： G06T15/04

摘要： A computer implemented method for generating a representation of structure for use in rendering a synthesized image is provided. The representation is a view-dependent displacement mapping that represents displacements along a viewing direction. This view dependency allows the representation to be used to determine self shadows as well as shading, occlusion and silhouettes when used during rendering for synthesis.

摘要翻译： 提供了一种用于生成用于渲染合成图像的结构的表示的计算机实现的方法。 该表示是视图相关的位移映射，其表示沿观察方向的位移。 该视图依赖性允许在用于合成的渲染期间使用表示来确定自身阴影以及阴影，遮挡和剪影。

公开(公告)号：US20070005345A1

公开(公告)日：2007-01-04

申请号：US11173892

申请日：2005-07-01

申请人： Ming Zhou ,  Heung-Yeung Shum

发明人： Ming Zhou ,  Heung-Yeung Shum

IPC分类号： G06F17/21

CPC分类号： G06F17/2881 ,  G06F17/2863

摘要： An approach of constructing Chinese language couplets, in particular, a second scroll sentence given a first scroll sentence is presented. The approach includes constructing a language model, a word translation-like model, and word association information such as mutual information values that can be used later in generating second scroll sentences of Chinese couplets. A Hidden Markov Model (HMM) is used to generate candidates. A Maximum Entropy (ME) model can then be used to re-rank the candidates to generate one or more reasonable second scroll sentences give a first scroll sentence.

摘要翻译： 提出了构建中文对联的方法，特别是给出第一滚动句的第二滚动句。 该方法包括构建语言模型，类似文字的模型，以及诸如可以在稍后生成中文对联的第二滚动句的互信息值之间的词关联信息。 隐马尔可夫模型（HMM）用于生成候选人。 然后可以使用最大熵（ME）模型来重新排列候选者以生成一个或多个合理的第二滚动句子给出第一滚动句子。

公开(公告)号：US20060290693A1

公开(公告)日：2006-12-28

申请号：US11158428

申请日：2005-06-22

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

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

IPC分类号： G06T17/00 ,  G06T17/20 ,  G06T15/30

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：US07133535B2

公开(公告)日：2006-11-07

申请号：US10328215

申请日：2002-12-21

申请人： Ying Huang ,  Stephen Ssu-te Lin ,  Baining Guo ,  Heung-Yeung Shum

发明人： Ying Huang ,  Stephen Ssu-te Lin ,  Baining Guo ,  Heung-Yeung Shum

IPC分类号： G06K9/00 ,  G10L215/00

CPC分类号： G06K9/00335 ,  G10L2021/105

摘要： A novel method for synchronizing the lips of a sketched face to an input voice. The lip synchronization system and method approach is to use training video as much as possible when the input voice is similar to the training voice sequences. Initially, face sequences are clustered from video segments, then by making use of sub-sequence Hidden Markov Models, a correlation between speech signals and face shape sequences is built. From this re-use of video, the discontinuity between two consecutive output faces is decreased and accurate and realistic synthesized animations are obtained. The lip synchronization system and method can synthesize faces from input audio in real-time without noticeable delay. Since acoustic feature data calculated from audio is directly used to drive the system without considering its phonemic representation, the method can adapt to any kind of voice, language or sound.

摘要翻译： 一种用于将草绘脸部的嘴唇同步到输入声音的新颖方法。 唇部同步系统和方法方法是当输入的声音类似于训练声音序列时尽可能多地使用训练视频。 最初，面部序列从视频片段聚类，然后通过利用子序列隐马尔可夫模型，构建了语音信号和面部形状序列之间的相关性。 从这种视频的再次使用，两个连续的输出面之间的不连续性被降低，并且获得准确而逼真的合成动画。 唇同步系统和方法可以实时地从输入音频合成面部，而没有明显的延迟。 由于从音频计算的声学特征数据直接用于驱动系统而不考虑其音素表示，该方法可以适应任何种类的语音，语言或声音。