专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US08009168B2 Real-time rendering of light-scattering media 有权
标题翻译：实时渲染光散射介质
公开(公告)号：US08009168B2
公开(公告)日：2011-08-30
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： G06T15/00
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。

2. 发明授权

US07990377B2 Real-time rendering of light-scattering media 有权
标题翻译：实时渲染光散射介质
公开(公告)号：US07990377B2
公开(公告)日：2011-08-02
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： G06T15/00
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。

3. 发明授权

US08233715B2 Probabilistic intensity similarity measure based on noise distributions 有权
标题翻译：基于噪声分布的概率强度相似性度量
公开(公告)号：US08233715B2
公开(公告)日：2012-07-31
申请号：US12110362
申请日：2008-04-28
申请人： Yasuyuki Matsushita , Stephen Ssu-te Lin
发明人： Yasuyuki Matsushita , Stephen Ssu-te Lin
IPC分类号： G06K9/46
CPC分类号： G06K9/00
摘要： Technologies for comparing observed intensities using a probabilistic similarity measure. In the probabilistic similarity measure example, there is no attempt to estimate a true intensity. Rather, the similarity of two observed intensities is defined as the likelihood that they each resulted from the same but unknown true identity while taking into account the noise characteristics of the camera observing the intensities. Since the true intensity is unknown, all possible true intensities are taken into account, rather than using a specific true intensity estimate. The probabilistic similarity measure indicates the degree to which two intensities correspond to the same intensity without estimating a true scene intensity value.
摘要翻译：使用概率相似性度量比较观察到的强度的技术。在概率相似性度量示例中，没有尝试估计真实强度。相反，两个观察到的强度的相似性被定义为它们各自由相同但未知的真实身份产生的可能性，同时考虑观察强度的相机的噪声特性。由于真实的强度是未知的，所有可能的真实强度都被考虑在内，而不是使用特定的真实强度估计。概率相似性度量表示两个强度对应于相同强度的程度，而不估计真实的场景强度值。

4. 发明申请

US20120147198A1 RADIOMETRIC CALIBRATION FROM NOISE DISTRIBUTIONS 有权
标题翻译：噪声分布的放射性校正
公开(公告)号：US20120147198A1
公开(公告)日：2012-06-14
申请号：US13400283
申请日：2012-02-20
申请人： Yasuyuki Matsushita , Stephen Ssu-te Lin
发明人： Yasuyuki Matsushita , Stephen Ssu-te Lin
IPC分类号： H04N17/00
CPC分类号： H04N5/217 , G06T5/002 , H04N5/2178 , H04N5/23229 , H04N5/357 , H04N17/002
摘要： Technologies that enable correcting for the non-linear relationship between scene irradiance and digital pixel intensity values of an image of the scene produced by a camera. Imaging noise is used as a signal from which a corrective function is derived. Noise distributions from the image are evaluated to determine the radiometric response function of the camera, from which an inverse response function is computed and used for calibration.
摘要翻译：能够校正场景辐照度与由摄像机产生的场景的图像的数字像素强度值之间的非线性关系的技术。成像噪声被用作导出校正功能的信号。评估来自图像的噪声分布以确定照相机的辐射响应函数，从其计算反应响应函数并用于校准。

5. 发明授权

US08149300B2 Radiometric calibration from noise distributions 有权
标题翻译：噪声分布的辐射校准
公开(公告)号：US08149300B2
公开(公告)日：2012-04-03
申请号：US12110357
申请日：2008-04-28
申请人： Yasuyuki Matsushita , Stephen Ssu-te Lin
发明人： Yasuyuki Matsushita , Stephen Ssu-te Lin
IPC分类号： H04N5/217 , G06K9/00
CPC分类号： H04N5/217 , G06T5/002 , H04N5/2178 , H04N5/23229 , H04N5/357 , H04N17/002
摘要： Technologies that enable correcting for the non-linear relationship between scene irradiance and digital pixel intensity values of an image of the scene produced by a camera. Imaging noise is used as a signal from which a corrective function is derived. Noise distributions from the image are evaluated to determine the radiometric response function of the camera, from which an inverse response function is computed and used for calibration.
摘要翻译：能够校正场景辐照度与由摄像机产生的场景的图像的数字像素强度值之间的非线性关系的技术。成像噪声被用作导出校正功能的信号。评估来自图像的噪声分布以确定照相机的辐射响应函数，从其计算反应响应函数并用于校准。

6. 发明申请

US20090268938A1 PROBABILISTIC INTENSITY SIMILARITY MEASURE BASED ON NOISE DISTRIBUTIONS 有权
标题翻译：基于噪声分布的概率强度相似度测度
公开(公告)号：US20090268938A1
公开(公告)日：2009-10-29
申请号：US12110362
申请日：2008-04-28
申请人： Yasuyuki Matsushita , Stephen Ssu-te Lin
发明人： Yasuyuki Matsushita , Stephen Ssu-te Lin
IPC分类号： G06K9/00
CPC分类号： G06K9/00
摘要： Technologies for comparing observed intensities using a probabilistic similarity measure. In the probabilistic similarity measure example, there is no attempt to estimate a true intensity. Rather, the similarity of two observed intensities is defined as the likelihood that they each resulted from the same but unknown true identity while taking into account the noise characteristics of the camera observing the intensities. Since the true intensity is unknown, all possible true intensities are taken into account, rather than using a specific true intensity estimate. The probabilistic similarity measure indicates the degree to which two intensities correspond to the same intensity without estimating a true scene intensity value.
摘要翻译：使用概率相似性度量比较观察到的强度的技术。在概率相似性度量示例中，没有尝试估计真实强度。相反，两个观察到的强度的相似性被定义为它们各自由相同但未知的真实身份产生的可能性，同时考虑观察强度的相机的噪声特性。由于真实的强度是未知的，所有可能的真实强度都被考虑在内，而不是使用特定的真实强度估计。概率相似性度量表示两个强度对应于相同强度的程度，而不估计真实场景强度值。

7. 发明授权

US07133535B2 System and method for real time lip synchronization 有权
标题翻译：用于实时唇形同步的系统和方法
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。

8. 发明授权

US08082129B2 Real-time rendering of light-scattering media 有权
公开(公告)号：US08082129B2
公开(公告)日：2011-12-20
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
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.

9. 发明申请

US20090268062A1 RADIOMETRIC CALIBRATION FROM NOISE DISTRIBUTIONS 有权
标题翻译：噪声分布的放射性校正
公开(公告)号：US20090268062A1
公开(公告)日：2009-10-29
申请号：US12110357
申请日：2008-04-28
申请人： Yasuyuki Matsushita , Stephen Ssu-te Lin
发明人： Yasuyuki Matsushita , Stephen Ssu-te Lin
IPC分类号： H04N5/217
CPC分类号： H04N5/217 , G06T5/002 , H04N5/2178 , H04N5/23229 , H04N5/357 , H04N17/002
摘要： Technologies that enable correcting for the non-linear relationship between scene irradiance and digital pixel intensity values of an image of the scene produced by a camera. Imaging noise is used as a signal from which a corrective function is derived. Noise distributions from the image are evaluated to determine the radiometric response function of the camera, from which an inverse response function is computed and used for calibration.
摘要翻译：能够校正场景辐照度与由摄像机产生的场景的图像的数字像素强度值之间的非线性关系的技术。成像噪声被用作导出校正功能的信号。评估来自图像的噪声分布以确定照相机的辐射响应函数，从其计算反应响应函数并用于校准。

10. 发明申请

US20090006047A1 Real-Time Rendering of Light-Scattering Media 有权
标题翻译：光散射介质的实时渲染
公开(公告)号：US20090006047A1
公开(公告)日：2009-01-01
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。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式