专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

41. 发明授权

US07212656B2 Rapid computer modeling of faces for animation 有权
公开(公告)号：US07212656B2
公开(公告)日：2007-05-01
申请号：US11275755
申请日：2006-01-26
申请人： Zicheng Liu , Zhengyou Zhang , Charles E. Jacobs , Michael F. Cohen
发明人： Zicheng Liu , Zhengyou Zhang , Charles E. Jacobs , Michael F. Cohen
IPC分类号： G06K9/00
CPC分类号： G06T13/40 , G06K9/00201 , G06K9/00248 , G06K9/00268 , G06K9/00281 , G06T7/251 , G06T7/55 , G06T7/579 , G06T7/74 , G06T9/001 , G06T15/205 , G06T17/00 , G06T17/10 , G06T17/20 , G06T2200/08 , G06T2207/10012 , G06T2207/10016 , G06T2207/10021 , G06T2207/30201 , H04N19/162 , H04N19/503
摘要： Described herein is a technique for creating a 3D face model using images obtained from an inexpensive camera associated with a general-purpose computer. Two still images of the user are captured, and two video sequences. The user is asked to identify five facial features, which are used to calculate a mask and to perform fitting operations. Based on a comparison of the still images, deformation vectors are applied to a neutral face model to create the 3D model. The video sequences are used to create a texture map. The process of creating the texture map references the previously obtained 3D model to determine poses of the sequential video images.

42. 发明授权

US07149330B2 Rapid computer modeling of faces for animation 有权
公开(公告)号：US07149330B2
公开(公告)日：2006-12-12
申请号：US11275754
申请日：2006-01-26
申请人： Zicheng Liu , Zhengyou Zhang , Charles E. Jacobs , Michael F. Cohen
发明人： Zicheng Liu , Zhengyou Zhang , Charles E. Jacobs , Michael F. Cohen
IPC分类号： G06K9/00
CPC分类号： G06T13/40 , G06K9/00201 , G06K9/00248 , G06K9/00268 , G06K9/00281 , G06T7/251 , G06T7/55 , G06T7/579 , G06T7/74 , G06T9/001 , G06T15/205 , G06T17/00 , G06T17/10 , G06T17/20 , G06T2200/08 , G06T2207/10012 , G06T2207/10016 , G06T2207/10021 , G06T2207/30201 , H04N19/162 , H04N19/503
摘要： Described herein is a technique for creating a 3D face model using images obtained from an inexpensive camera associated with a general-purpose computer. Two still images of the user are captured, and two video sequences. The user is asked to identify five facial features, which are used to calculate a mask and to perform fitting operations. Based on a comparison of the still images, deformation vectors are applied to a neutral face model to create the 3D model. The video sequences are used to create a texture map. The process of creating the texture map references the previously obtained 3D model to determine poses of the sequential video images.

43. 发明授权

US07126602B2 Interactive horizon mapping 有权
公开(公告)号：US07126602B2
公开(公告)日：2006-10-24
申请号：US10983359
申请日：2004-11-08
申请人： Peter-Pike Sloan , Michael F. Cohen
发明人： Peter-Pike Sloan , Michael F. Cohen
IPC分类号： G06T15/50
CPC分类号： G06T15/60
摘要： Shadows, which play an important role in perceiving the shape and texture of an object, are simulated interactively in a real time, self-shadowing of a bump mapped surface for a computer rendered object. A computer graphics textured object function defines a horizon map over an orientation in a tangent space of the object using different textures or basis functions. The implementation can be performed using commodity graphics hardware by precomputing the horizon map for limited visibility for each point on the bump mapped surface given light in each of a plurality of radial directions. The horizon map is used to produce self-shadowing of the bump mapped surface of the object.

44. 发明授权

US07091975B1 Shape and animation methods and systems using examples 有权
标题翻译：形状和动画方法和系统使用示例
公开(公告)号：US07091975B1
公开(公告)日：2006-08-15
申请号：US09627147
申请日：2000-07-21
申请人： Michael F. Cohen , Charles F. Rose, III , Peter-Pike Sloan
发明人： Michael F. Cohen , Charles F. Rose, III , Peter-Pike Sloan
IPC分类号： G06T15/70
CPC分类号： G06T13/40 , Y10S345/949 , Y10S345/956
摘要： Modern animation and modeling systems enable artists to create high-quality content, but provide limited support for interactive applications. Although complex forms and motions can be constructed either by hand or with motion or geometry capture technologies, once they are created, they are difficult to modify, particularly at runtime. Interpolation provides a way to leverage artist-generated source material. Presented here are methodologies for efficient runtime interpolation between multiple forms or multiple motion segments. Radial basis functions provide key mathematical support for the interpolation. Once the illustrated and described system is provided with example forms and motions, it generates a continuous range of forms referred to as a “shape” or a continuous range of motions referred to as a verb. Additionally, shape interpolation methodology is applied to articulated figures to create smoothly skinned figures that deform in natural ways. The runtime interpolation of the forms or motions runs fast enough to be used in interactive applications such as games.
摘要翻译：现代动画和建模系统使艺术家能够创建高质量的内容，但对交互式应用程序提供有限的支持。虽然复杂的形式和运动可以手工或运动或几何捕获技术构建，但一旦创建，它们就难以修改，特别是在运行时。插值提供了一种利用艺术家生成的素材的方法。这里提出了用于在多个形式或多个运动段之间高效运行时间插值的方法。径向基函数为插值提供关键的数学支持。一旦所示出和描述的系统被提供有示例形式和运动，它就产生被称为“形状”的连续范围或被称为动词的连续运动范围。此外，形状插值方法应用于铰接图形，以创建平滑的皮肤图形，以自然的方式变形。表单或动作的运行时插值运行得足够快，可用于诸如游戏的交互式应用程序。

45. 发明授权

US06980671B2 Rapid computer modeling of faces for animation 有权
公开(公告)号：US06980671B2
公开(公告)日：2005-12-27
申请号：US10846086
申请日：2004-05-14
申请人： Zicheng Liu , Zhengyou Zhang , Michael F. Cohen , Charles E. Jacobs
发明人： Zicheng Liu , Zhengyou Zhang , Michael F. Cohen , Charles E. Jacobs
IPC分类号： G06K9/00 , G06T13/40 , G06T15/20 , G06T17/00 , G06T17/10 , H04N7/26 , H04N7/36
CPC分类号： G06T13/40 , G06K9/00201 , G06K9/00248 , G06K9/00268 , G06K9/00281 , G06T7/251 , G06T7/55 , G06T7/579 , G06T7/74 , G06T9/001 , G06T15/205 , G06T17/00 , G06T17/10 , G06T17/20 , G06T2200/08 , G06T2207/10012 , G06T2207/10016 , G06T2207/10021 , G06T2207/30201 , H04N19/162 , H04N19/503
摘要： Described herein is a technique for creating a 3D face model using images obtained from an inexpensive camera associated with a general-purpose computer. Two still images of the user are captured, and two video sequences. The user is asked to identify five facial features, which are used to calculate a mask and to perform fitting operations. Based on a comparison of the still images, deformation vectors are applied to a neutral face model to create the 3D model. The video sequences are used to create a texture map. The process of creating the texture map references the previously obtained 3D model to determine poses of the sequential video images.

46. 发明授权

US4928250A System for deriving radiation images 失效
标题翻译：用于导出辐射图像的系统
公开(公告)号：US4928250A
公开(公告)日：1990-05-22
申请号：US881067
申请日：1986-07-02
申请人： Donald P. Greenberg , Michael F. Cohen , Eric A. Haines
发明人： Donald P. Greenberg , Michael F. Cohen , Eric A. Haines
IPC分类号： G06T15/55
CPC分类号： G06T15/55
摘要： In an algorithm for deriving radiation images, where view independent radiation calculations are precomputed so that they do not need to be repeated for every view of the same environment. To find the form factors for radiosity techniques, a hemi-cube is constructed around the surface with grid cells defined for all faces on the hemi-cube. All other surfaces in the environment are projected onto the hemi-cube to facilitate the form factor calculations. A novel ray-tracing technique is disclosed where a light buffer in the form of a cube is constructed around each radiation source and grid cells are defined on the faces of the cube. Surfaces in the environment are projected onto the cube and the depths from the source are stored for each grid cell to facilitate shadow testing. Light reflected off of the viewed surface from another surface may be modeled by determining mirror positions of the viewer and the image plane. Instead of storing the depths of surfaces from the viewer or the radiation source, the identity of the polygons in the environment are stored instead to speed up the calculations. Scan conversion hardware is used to accelerate each of these operations. In a graphics pipeline, a feedback path is provided from the image processor to the CPU memory to store the result of the form factor or light buffer pre-computations to speed up the radiosity and ray-tracing calculations by several orders of magnitude.
摘要翻译：在用于导出辐射图像的算法中，其中预先计算视图独立辐射计算，使得它们不需要针对相同环境的每个视图重复。为了找到辐射度技术的形状因子，在表面周围构造半立方体，并为半立方体上的所有面定义网格单元。环境中的所有其他表面投影到半立方体上，以便于形状因子计算。公开了一种新颖的光线跟踪技术，其中围绕每个辐射源构造立方体形式的光缓冲器，并且在立方体的面上限定网格单元。将环境中的曲面投影到立方体上，并为每个网格单元存储来自源的深度，以便于阴影测试。可以通过确定观察者和图像平面的镜像位置来对来自另一表面的观看表面反射的光进行建模。代替存储来自观察者或辐射源的表面的深度，而不是存储环境中的多边形的身份来加速计算。扫描转换硬件用于加速这些操作。在图形管线中，从图像处理器向CPU存储器提供反馈路径以存储形状因子或光缓冲器预计算的结果，以将辐射度和光线跟踪计算加速几个数量级。

47. 发明授权

US08872850B2 Juxtaposing still and dynamic imagery for cliplet creation 有权
标题翻译：并列创作的静态和动态图像
公开(公告)号：US08872850B2
公开(公告)日：2014-10-28
申请号：US13411651
申请日：2012-03-05
申请人： Neel Suresh Joshi , Sisil Sanjeev Mehta , Michael F. Cohen , Steven M. Drucker , Hugues Hoppe , Matthieu Uyttendaele
发明人： Neel Suresh Joshi , Sisil Sanjeev Mehta , Michael F. Cohen , Steven M. Drucker , Hugues Hoppe , Matthieu Uyttendaele
IPC分类号： G09G5/377
CPC分类号： G11B27/031 , G06T11/60 , G06T13/80 , G06T15/503 , G11B27/34
摘要： Various technologies described herein pertain to juxtaposing still and dynamic imagery to create a cliplet. A first subset of a spatiotemporal volume of pixels in an input video can be set as a static input segment, and the static input segment can be mapped to a background of the cliplet. Further, a second subset of the spatiotemporal volume of pixels in the input video can be set as a dynamic input segment based on a selection of a spatial region, a start time, and an end time within the input video. Moreover, the dynamic input segment can be refined spatially and/or temporally and mapped to an output segment of the cliplet within at least a portion of output frames of the cliplet based on a predefined temporal mapping function, and the output segment can be composited over the background for the output frames of the cliplet.
摘要翻译：这里描述的各种技术与并置静态和动态图像以创建小屋。可以将输入视频中的时空体积像素的第一子集设置为静态输入段，静态输入段可以映射到小区的背景。此外，可以基于输入视频内的空间区域，开始时间和结束时间的选择，将输入视频中的时空体积像素的第二子集设置为动态输入片段。此外，基于预定义的时间映射函数，动态输入段可以在空间上和/或时间上精细化并且被映射到小块的输出帧的至少一部分内的小区的输出段，并且输出段可以被合成背景为小猫的输出框架。

48. 发明授权

US08619071B2 Image view synthesis using a three-dimensional reference model 有权
标题翻译：使用三维参考模型的图像视图合成
公开(公告)号：US08619071B2
公开(公告)日：2013-12-31
申请号：US12211596
申请日：2008-09-16
申请人： Johannes P. Kopf , Michael F. Cohen , Daniel Lischinski , Matthieu T. Uyttendaele
发明人： Johannes P. Kopf , Michael F. Cohen , Daniel Lischinski , Matthieu T. Uyttendaele
IPC分类号： G06T15/00 , G09G5/02
CPC分类号： G06T15/20
摘要： A novel image view may be synthesized using a three-dimensional reference model. In an example embodiment, a device-implemented method for synthesizing a novel image view includes acts of registering, selecting, applying and synthesizing. An image is registered to at least one reference model. A source block of visual data from the image is selected with regard to a destination block of the reference model based on a source depth associated with the source block and a destination depth associated with the destination block. The destination position of the destination block of the reference model is not visible in the image. The source block of visual data from the image is applied to the destination block of the reference model to produce an image-augmented model. A novel image view is synthesized using the image-augmented model.
摘要翻译：可以使用三维参考模型来合成新颖的图像视图。在示例性实施例中，用于合成新颖图像视图的设备实现方法包括注册，选择，应用和合成的动作。图像被注册到至少一个参考模型。基于与源块相关联的源深度和与目的地块相关联的目的地深度，针对参考模型的目的地块来选择来自图像的视觉数据的源块。参考模型的目的地块的目标位置在图像中不可见。来自图像的视觉数据的源块被应用于参考模型的目的地块以产生图像增强模型。使用图像增强模型合成新颖的图像视图。

49. 发明申请

US20110069089A1 POWER MANAGEMENT FOR ORGANIC LIGHT-EMITTING DIODE (OLED) DISPLAYS 审中-公开
标题翻译：有机发光二极管（OLED）显示器的电源管理
公开(公告)号：US20110069089A1
公开(公告)日：2011-03-24
申请号：US12610834
申请日：2009-11-02
申请人： Johannes P. Kopf , Georg F. Petschnigg , Michael F. Cohen
发明人： Johannes P. Kopf , Georg F. Petschnigg , Michael F. Cohen
IPC分类号： G09G5/10 , G09G5/00 , G09G3/30
CPC分类号： G09G3/3208 , G09G2320/0271 , G09G2320/0626 , G09G2320/066 , G09G2330/021 , G09G2360/16
摘要： Embodiments of power management for OLED displays are described. In various embodiments, power consumption for an OLED display can be managed by adjusting brightness of individual pixels. An input image can be obtained and processed using an algorithm that reduces brightness and maintains perceived contrast. This can involve computing a difference value associated with individual pixels of the image to account for perceived contrast and computing a reduced brightness value for the pixel using the difference value. An ultra-low power mode in which power consumption of the OLED display is adjusted semantically can be employed for a low brightness range. The algorithm and the ultra-low power mode can be combined to provide a continuous range of adjustment for the OLED display.
摘要翻译：描述了用于OLED显示器的电源管理的实施例。在各种实施例中，可以通过调整各个像素的亮度来管理OLED显示器的功耗。可以使用降低亮度并维持感知对比度的算法来获得和处理输入图像。这可以包括计算与图像的各个像素相关联的差值，以考虑感知到的对比度并使用差值计算像素的降低的亮度值。对于低亮度范围，可以采用在语义上调整OLED显示器的功耗的超低功耗模式。该算法和超低功耗模式可以组合，为OLED显示器提供连续的调整范围。

50. 发明授权

US07889949B2 Joint bilateral upsampling 有权
标题翻译：联合双边采样
公开(公告)号：US07889949B2
公开(公告)日：2011-02-15
申请号：US11742325
申请日：2007-04-30
申请人： Michael F. Cohen , Matthew T. Uyttendaele , Daniel Lischinski , Johannes Kopf
发明人： Michael F. Cohen , Matthew T. Uyttendaele , Daniel Lischinski , Johannes Kopf
IPC分类号： G06K9/32
CPC分类号： G06T3/4007
摘要： A “Joint Bilateral Upsampler” uses a high-resolution input signal to guide the interpolation of a low-resolution solution set (derived from a downsampled version of the input signal) from low-to high-resolution. The resulting high-resolution solution set is then saved or applied to the original input signal to produce a high-resolution output signal. The high-resolution solution set is close to what would be produced directly from the input signal without downsampling. However, since the high-resolution solution set is constructed in part from a downsampled version of the input signal, it is computed using significantly less computational overhead and memory than a solution set computed directly from a high-resolution signal. Consequently, the Joint Bilateral Upsampler is advantageous for use in near real-time operations, in applications where user wait times are important, and in systems where computational costs and available memory are limited.
摘要翻译： “联合双边上行采样器”使用高分辨率输入信号来引导低分辨率解集（从输入信号的下采样版本导出）的内插从低到高分辨率。然后将所得到的高分辨率解决方案集保存或应用于原始输入信号以产生高分辨率输出信号。高分辨率解决方案集合接近于直接从输入信号产生的，而无需采样。然而，由于高分辨率解集合部分地由输入信号的下采样版本构成，所以与直接从高分辨率信号计算的解集相比，使用显着更少的计算开销和存储器来计算。因此，联合双边上行采样器在用户等待时间重要的应用中以及在计算成本和可用存储器受到限制的系统中有利于近实时操作。

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