-
公开(公告)号：US20140210810A1
公开(公告)日：2014-07-31
申请号：US13755932
申请日：2013-01-31
IPC分类号： G06T19/00
CPC分类号： H04N13/111 , H04N13/275
摘要： Systems and methods are provided that allow for the rapid creation of multiple novel views for applications. These multiple views may allow for not only stereo views but also for different viewpoints of a stereographic scene to be presented, or for a time progression of the stereo scene to be presented, where a viewpoint is altered with respect to time. The systems and methods may be employed to create the content for auto-stereographic displays or multiple view systems that use a plurality of novel views to display stereo media. Such displays or multiple view systems may include those employing parallax barriers or lenticular lenses.
摘要翻译： 提供了允许为应用程序快速创建多个新颖视图的系统和方法。 这些多个视图不仅可以允许立体视图，而且可以允许要呈现的立体场景的不同视点，或者允许要呈现的立体场景的时间进度，其中视点相对于时间被改变。 可以采用系统和方法来创建用于自动立体显示器或使用多个新颖视图来显示立体声媒体的多视图系统的内容。 这种显示器或多视图系统可以包括采用视差屏障或双凸透镜的那些。
-
2.发明申请公开(公告)号：US20110110561A1
公开(公告)日：2011-05-12
申请号：US12938317
申请日：2010-11-02
申请人： Parag Havaldar
发明人： Parag Havaldar
IPC分类号： G06K9/00
CPC分类号： G06T13/40 , G06T7/251 , G06T2207/30201 , G06T2207/30204
摘要： Capturing facial surface using marker patterns laid out on the facial surface by adapting the marker patterns to contours of the facial surface and motion range of a head including: generating a facial action coding system (FACS) matrix by capturing FACS poses; generating a pattern to wrap over the facial surface using the FACS poses as a guide; capturing and tracking marker motions of the pattern; stabilizing the marker motions of the pattern using a head stabilization transform to remove head motions from the marker motions; and generating and applying a plurality of FACS matrix weights to the stabilized marker motions.
摘要翻译： 通过使标记图案适应面部表面的轮廓和头部的运动范围来捕捉面部表面上布置的标记图案，包括：通过捕获FACS姿态来产生面部动作编码系统（FACS）矩阵; 使用FACS姿势产生用于覆盖面部表面的图案作为指导; 捕获和跟踪图案的标记运动; 使用头部稳定变换来稳定图案的标记运动，以从标记运动中去除头部运动; 以及将多个FACS矩阵权重生成并应用于所述稳定的标记运动。
-
公开(公告)号：US09621869B2
公开(公告)日：2017-04-11
申请号：US13649720
申请日：2012-10-11
申请人： Alan L. Davidson , Parag Havaldar , Peter H. Palombi , Josh Wills
发明人： Alan L. Davidson , Parag Havaldar , Peter H. Palombi , Josh Wills
CPC分类号： H04N13/111 , G06T7/00 , H04N13/122
摘要： Systems and methods are provided for minimizing re-projection artifacts. From a re-projection method, a distortion map determines areas of excessive stretching or compressing of pixels, which are then rendered. The re-projection and render are composited to create a new stereo image. Systems and methods are also provided for a “depth layout” process, whereby a new offset view of a 2D plate is created, allowing a stereo pair of images. Custom geometry that approximates the scene is created and 2D rotoscoping is employed to cut out shapes from the geometry. A depth map is created, from which an offset image may be re-projected, resulting in a stereo pair. Systems and methods are also provided for a fast re-projection technique, which creates a novel view from an existing image. The process generates a disparity map and then a distortion map, which is then used to create the new view.
-
公开(公告)号：US08279228B2
公开(公告)日：2012-10-02
申请号：US12986095
申请日：2011-01-06
申请人： Parag Havaldar , Mark Sagar , Josh Ochoa
发明人： Parag Havaldar , Mark Sagar , Josh Ochoa
IPC分类号： G06T13/00
CPC分类号： G06T13/40
摘要： A method of animating a digital facial model, the method including: defining a plurality of action units; calibrating each action unit of the plurality of action units via an actor's performance; capturing first facial pose data; determining a plurality of weights, each weight of the plurality of weights uniquely corresponding to the each action unit, the plurality of weights characterizing a weighted combination of the plurality of action units, the weighted combination approximating the first facial pose data; generating a weighted activation by combining the results of applying the each weight to the each action unit; applying the weighted activation to the digital facial model; and recalibrating at least one action unit of the plurality of action units using input user adjustments to the weighted activation.
摘要翻译： 一种动画化数字面部模型的方法，所述方法包括：定义多个动作单元; 通过演员的表演来校准多个动作单元中的每个动作单元; 捕获第一面部姿势数据; 确定多个权重，所述权重唯一地对应于每个动作单元，所述多个权重表征所述多个动作单元的加权组合，所述加权组合近似所述第一面部姿势数据; 通过将应用每个权重的结果组合到每个动作单元来产生加权激活; 将加权激活应用于数字面部模型; 以及使用对所述加权激活的输入用户调整来重新校准所述多个动作单元中的至少一个动作单元。
-
公开(公告)号：US07606392B2
公开(公告)日：2009-10-20
申请号：US11467512
申请日：2006-08-25
CPC分类号： G06K9/00255 , G06T7/246
摘要： Capturing and processing facial motion data includes: coupling a plurality of sensors to target points on a facial surface of an actor; capturing frame by frame images of the plurality of sensors disposed on the facial surface of the actor using at least one motion capture camera disposed on a head-mounted system; performing, in the head-mounted system, a tracking function on the frame by frame images of the plurality of sensors to accurately map the plurality of sensors for each frame; and generating, in the head-mounted system, a modeled surface representing the facial surface of the actor.
摘要翻译： 捕获和处理面部运动数据包括：将多个传感器耦合到演员的面部表面上的目标点; 使用设置在头戴式系统上的至少一个运动捕捉相机来捕获布置在所述演员的面部表面上的多个传感器的逐帧图像; 在头戴式系统中，对多个传感器的逐帧图像执行跟踪功能，以准确地映射每个帧的多个传感器; 并且在头戴式系统中产生表示演员的面部表面的模型表面。
-
6.发明申请METHOD AND SYSTEM FOR ENSURING STEREO ALIGNMENT DURING PIPELINE PROCESSING 审中-公开用于在管道加工过程中保持立体对准的方法和系统公开(公告)号：US20140003706A1
公开(公告)日：2014-01-02
申请号：US13755461
申请日：2013-01-31
IPC分类号： G06K9/00
CPC分类号： G06K9/00201 , G06T5/006 , G06T2207/10021
摘要： Apparatus and methods are provided to implement a technique for adjusting images, such as for addressing lens distortions. In one implementation, a computer system uses un-warping to address differences between two camera lenses. After unwarping two stereo images, the images are re-warped but re-warped using a common set of parameters.
摘要翻译： 提供了设备和方法来实现用于调整图像的技术，例如用于寻址透镜失真。 在一个实现中，计算机系统使用不翘曲来解决两个相机镜头之间的差异。 在不正确的两个立体图像之后，图像被重新翘曲，但是使用一组通用的参数重新翘曲。
-
公开(公告)号：US20130314501A1
公开(公告)日：2013-11-28
申请号：US13649720
申请日：2012-10-11
申请人： Alan L. Davidson , Parag Havaldar , Peter H. Palombi , Josh Wills
发明人： Alan L. Davidson , Parag Havaldar , Peter H. Palombi , Josh Wills
IPC分类号： H04N13/02
CPC分类号： H04N13/111 , G06T7/00 , H04N13/122
摘要： Systems and methods are provided for minimizing re-projection artifacts. From a re-projection method, a distortion map determines areas of excessive stretching or compressing of pixels, which are then rendered. The re-projection and render are composited to create a new stereo image. Systems and methods are also provided for a “depth layout” process, whereby a new offset view of a 2D plate is created, allowing a stereo pair of images. Custom geometry that approximates the scene is created and 2D rotoscoping is employed to cut out shapes from the geometry. A depth map is created, from which an offset image may be re-projected, resulting in a stereo pair. Systems and methods are also provided for a fast re-projection technique, which creates a novel view from an existing image. The process generates a disparity map and then a distortion map, which is then used to create the new view.
摘要翻译： 提供了系统和方法以最小化重新投影伪像。 从再投影方法，失真图确定过度拉伸或压缩像素的区域，然后再渲染。 重新投影和渲染被合成以创建新的立体图像。 还提供了用于“深度布局”过程的系统和方法，由此创建2D板的新偏移视图，允许立体图像对。 创建近似场景的自定义几何，并使用2D旋转坐标来切割几何形状。 创建深度图，可以重新投影偏移图像，导致立体对。 还提供了用于快速重新投影技术的系统和方法，其从现有图像创建新颖的视图。 该过程生成视差映射，然后生成失真映射，然后用于创建新视图。
-
公开(公告)号：US20110175921A1
公开(公告)日：2011-07-21
申请号：US12986095
申请日：2011-01-06
申请人： Parag Havaldar , Mark Sagar , Josh Ochoa
发明人： Parag Havaldar , Mark Sagar , Josh Ochoa
IPC分类号： G06T13/00
CPC分类号： G06T13/40
摘要： A method of animating a digital facial model, the method including: defining a plurality of action units; calibrating each action unit of the plurality of action units via an actor's performance; capturing first facial pose data; determining a plurality of weights, each weight of the plurality of weights uniquely corresponding to the each action unit, the plurality of weights characterizing a weighted combination of the plurality of action units, the weighted combination approximating the first facial pose data; generating a weighted activation by combining the results of applying the each weight to the each action unit; applying the weighted activation to the digital facial model; and recalibrating at least one action unit of the plurality of action units using input user adjustments to the weighted activation.
摘要翻译： 一种动画化数字面部模型的方法，所述方法包括：定义多个动作单元; 通过演员的表演来校准多个动作单元中的每个动作单元; 捕获第一面部姿势数据; 确定多个权重，所述权重唯一地对应于每个动作单元，所述多个权重表征所述多个动作单元的加权组合，所述加权组合近似所述第一面部姿势数据; 通过将应用每个权重的结果组合到每个动作单元来产生加权激活; 将加权激活应用于数字面部模型; 以及使用对所述加权激活的输入用户调整来重新校准所述多个动作单元中的至少一个动作单元。
-
公开(公告)号：US07733346B2
公开(公告)日：2010-06-08
申请号：US11829731
申请日：2007-07-27
申请人： Demian Gordon , Parag Havaldar
发明人： Demian Gordon , Parag Havaldar
IPC分类号： G06T13/00
CPC分类号： G06T13/40 , G06T7/246 , G06T2207/10016 , G06T2207/30201
摘要： A method, comprising: generating facial muscle activations from facial marker data; animating a computer graphics facial model using the facial muscle activations; generating a skin layer overlaying the computer graphics facial model; and animating the skin layer using the facial marker data.
摘要翻译： 一种方法，包括：从面部标记数据产生面部肌肉激活; 使用面部肌肉激活来动画化计算机图形面部模型; 生成覆盖计算机图形面部模型的皮肤层; 以及使用面部标记数据来动画化皮肤层。
-
公开(公告)号：US10931927B2
公开(公告)日：2021-02-23
申请号：US13755932
申请日：2013-01-31
IPC分类号： G06T15/00 , H04N13/111 , H04N13/275
摘要： Systems and methods are provided that allow for the rapid creation of multiple novel views for applications. These multiple views may allow for not only stereo views but also for different viewpoints of a stereographic scene to be presented, or for a time progression of the stereo scene to be presented, where a viewpoint is altered with respect to time. The systems and methods may be employed to create the content for auto-stereographic displays or multiple view systems that use a plurality of novel views to display stereo media. Such displays or multiple view systems may include those employing parallax barriers or lenticular lenses.
-
-
-
-
-
-
-
-
-
搜索结果
22 条记录 (耗时 0.025 秒)
