-
公开(公告)号：US20140099026A1
公开(公告)日：2014-04-10
申请号：US13647594
申请日：2012-10-09
IPC分类号： G06K9/00
CPC分类号： H04N1/6027 , H04N1/6072 , H04N1/6075 , H04N1/6077 , H04N1/6086 , H04N9/643 , H04N9/73 , H04N21/44008 , H04N21/4402 , H04N21/4788 , H04N21/8153
摘要： In some implementations, a method provides color corrections based on multiple images. In some implementations, a method includes determining one or more characteristics of each of a plurality of source images and determining one or more similarities between the one or more characteristics of different source images. The source images are grouped into one or more groups of one or more target images based on the determined similarities. The method determines and applies one or more color corrections to the one or more target images in at least one of the groups.
摘要翻译： 在一些实现中，一种方法提供了基于多个图像的颜色校正。 在一些实施方式中，一种方法包括确定多个源图像中的每一个的一个或多个特征并确定不同源图像的一个或多个特征之间的一个或多个相似度。 基于所确定的相似度，源图像被分组成一组或多组一个或多个目标图像。 该方法确定并应用一个或多个颜色校正到至少一个组中的一个或多个目标图像。
-
2.发明授权公开(公告)号：US09280804B2
公开(公告)日：2016-03-08
申请号：US13678850
申请日：2012-11-16
摘要： In some implementations, a method rotates images based on image content to correct image orientation. In some implementations, a method includes obtaining one or more identifications of content depicted in an image and determining a current orientation of the content depicted in the image. The current orientation is determined based on the one or more identifications of the content. An amount of rotation for the image is determined that orients the content closer to a predetermined reference orientation than to the current orientation. The image is rotated by the determined amount.
摘要翻译： 在一些实现中，方法基于图像内容旋转图像以校正图像取向。 在一些实施方式中，一种方法包括获得在图像中描绘的内容的一个或多个标识，并确定图像中描绘的内容的当前方位。 基于内容的一个或多个标识来确定当前方向。 确定图像的旋转量，使得内容定向比预定的参考方向更接近于当前方位。 图像旋转确定的量。
-
公开(公告)号：US09002109B2
公开(公告)日：2015-04-07
申请号：US13647594
申请日：2012-10-09
IPC分类号： G06K9/00 , H04N1/60 , H04N9/64 , H04N9/73 , H04N21/44 , H04N21/4402 , H04N21/4788 , H04N21/81
CPC分类号： H04N1/6027 , H04N1/6072 , H04N1/6075 , H04N1/6077 , H04N1/6086 , H04N9/643 , H04N9/73 , H04N21/44008 , H04N21/4402 , H04N21/4788 , H04N21/8153
摘要： In some implementations, a method provides color corrections based on multiple images. In some implementations, a method includes determining one or more characteristics of each of a plurality of source images and determining one or more similarities between the one or more characteristics of different source images. The source images are grouped into one or more groups of one or more target images based on the determined similarities. The method determines and applies one or more color corrections to the one or more target images in at least one of the groups.
摘要翻译： 在一些实现中，一种方法提供了基于多个图像的颜色校正。 在一些实施方式中，一种方法包括确定多个源图像中的每一个的一个或多个特征并且确定不同源图像的一个或多个特征之间的一个或多个相似度。 基于所确定的相似度，源图像被分组成一组或多组一个或多个目标图像。 该方法确定并应用一个或多个颜色校正到至少一个组中的一个或多个目标图像。
-
4.发明申请公开(公告)号：US20140140609A1
公开(公告)日：2014-05-22
申请号：US13678850
申请日：2012-11-16
IPC分类号： G06T3/60
摘要： In some implementations, a method rotates images based on image content to correct image orientation. In some implementations, a method includes obtaining one or more identifications of content depicted in an image and determining a current orientation of the content depicted in the image. The current orientation is determined based on the one or more identifications of the content. An amount of rotation for the image is determined that orients the content closer to a predetermined reference orientation than to the current orientation. The image is rotated by the determined amount.
摘要翻译： 在一些实现中，方法基于图像内容旋转图像以校正图像取向。 在一些实施方式中，一种方法包括获得在图像中描绘的内容的一个或多个标识，并确定图像中描绘的内容的当前方位。 基于内容的一个或多个标识来确定当前方向。 确定图像的旋转量，使得内容定向比预定的参考方向更接近于当前方位。 图像旋转确定的量。
-
5.发明授权Methods and apparatus for determining local coordinate frames for a human hand 有权用于确定人手的局部坐标系的方法和装置公开(公告)号：US08553001B2
公开(公告)日：2013-10-08
申请号：US13069197
申请日：2011-03-22
申请人： Aravind Krishnaswamy
发明人： Aravind Krishnaswamy
IPC分类号： G06F3/041
CPC分类号： G06F3/04883 , G06F2203/04808
摘要： Methods and apparatus for providing a local coordinate frame are described. A user may place the tips of all five digits on a multitouch user interface with a natural gesture to provide five touch points. A local coordinate frame may be constructed from the touch points. A local coordinate frame may be computed relative to the entire hand and/or relative to each individual digit. The technique may be agnostic in regard to the orientation of the device and to which hand is used. The user may move or rotate their hand, and the local coordinate frame is adjusted to the new positioning relative to the device. The technique may also infer a relative position of the palm from the digit input points, allowing the display of user interface elements where the elements are visible rather than occluded by the hand.
摘要翻译： 描述了用于提供局部坐标系的方法和装置。 用户可以将自然姿态的所有五位数字的提示放在多点触控用户界面上，以提供五个接触点。 可以从触摸点构建局部坐标系。 可以相对于整个手和/或相对于每个单独的数字计算局部坐标系。 关于装置的方向和使用哪一只手，该技术可能是不可知的。 用户可以移动或旋转他们的手，并且将局部坐标系调整到相对于设备的新定位。 该技术还可以推断手掌从数字输入点的相对位置，允许显示用户界面元素，其中元素可见而不是被手遮挡。
-
6.发明授权System and method for simulation of paint deposition using a pickup and reservoir model 有权使用拾取和储层模型模拟油漆沉积的系统和方法公开(公告)号：US08462173B2
公开(公告)日：2013-06-11
申请号：US12862879
申请日：2010-08-25
CPC分类号： G06T11/40
摘要： Systems, methods, and apparatus for simulating natural media painting in a digital painting application (or painting simulation module) using a two-layer model of a virtual paint brush may more accurately simulate real world painting techniques than conventional painting simulations. A two-layer brush model may include a reservoir buffer and a pickup buffer to separately represent the paint stored in the belly of a paint brush tip and paint that has been picked up on the surface of the brush tip during a brush stoke, respectively. The two-layer brush model may also include methods that automatically control how virtual paint moves between these layers and a digital canvas. In simulations that employ this two-layer brush model, virtual paint may be deposited on the digital canvas directly from both of the buffers. The amount of paint deposited from each buffer (and/or the ratio of the amounts) may be configurable by a user.
摘要翻译： 使用虚拟油漆刷的两层模型在数字绘画应用（或绘画模拟模块）中模拟自然媒体绘画的系统，方法和装置可以比常规绘画模拟更准确地模拟真实世界的绘画技术。 双层刷子模型可以包括储存器缓冲器和拾取缓冲器，以分别表示在刷子刷头期间被存储在刷子尖端的腹部中的涂料和在刷头表面上被拾取的涂料。 双层刷子模型还可以包括自动控制虚拟绘图在这些层之间移动以及数字画布的方法。 在使用这种双层刷子模型的模拟中，虚拟油漆可以直接从两个缓冲器沉积在数字画布上。 从每个缓冲液沉积的油漆量（和/或量的比例）可由用户配置。
-
7.发明申请Methods and Apparatus for Determining Local Coordinate Frames for a Human Hand 有权用于确定人手的局部坐标框架的方法和装置公开(公告)号：US20130127733A1
公开(公告)日：2013-05-23
申请号：US13069197
申请日：2011-03-22
申请人： Aravind Krishnaswamy
发明人： Aravind Krishnaswamy
IPC分类号： G06F3/041
CPC分类号： G06F3/04883 , G06F2203/04808
摘要： Methods and apparatus for providing a local coordinate frame are described. A user may place the tips of all five digits on a multitouch user interface with a natural gesture to provide five touch points. A local coordinate frame may be constructed from the touch points. A local coordinate frame may be computed relative to the entire hand and/or relative to each individual digit. The technique may be agnostic in regard to the orientation of the device and to which hand is used. The user may move or rotate their hand, and the local coordinate frame is adjusted to the new positioning relative to the device. The technique may also infer a relative position of the palm from the digit input points, allowing the display of user interface elements where the elements are visible rather than occluded by the hand.
摘要翻译： 描述了用于提供局部坐标系的方法和装置。 用户可以将自然姿态的所有五位数字的提示放在多点触控用户界面上，以提供五个接触点。 可以从触摸点构建局部坐标系。 可以相对于整个手和/或相对于每个单独的数字计算局部坐标系。 关于装置的方向和使用哪一只手，该技术可能是不可知的。 用户可以移动或旋转他们的手，并且将局部坐标系调整到相对于设备的新定位。 该技术还可以推断手掌从数字输入点的相对位置，允许显示用户界面元素，其中元素可见而不是被手遮挡。
-
8.发明申请PREVENTING PIXEL MODIFICATION OF AN IMAGE BASED ON A METRIC INDICATING DISTORTION IN A 2D REPRESENTATION OF A 3D OBJECT 有权在3D对象的二维表示中，基于指标变化的图像预处理像素修改公开(公告)号：US20130121612A1
公开(公告)日：2013-05-16
申请号：US12202173
申请日：2008-08-29
申请人： Peter F. Falco, JR. , Gavin S.P Miller , Michael O. Clifton , Nathan A. Carr , Nikolai Svakhin , Aravind Krishnaswamy
发明人： Peter F. Falco, JR. , Gavin S.P Miller , Michael O. Clifton , Nathan A. Carr , Nikolai Svakhin , Aravind Krishnaswamy
IPC分类号： G06K9/03
CPC分类号： G06T11/00
摘要： A method, system, and computer-readable storage medium are disclosed for distortion-based mask generation. A respective distortion metric may be determined at each location of a plurality of locations in a two-dimensional representation of a three-dimensional object. The two-dimensional representation may be based on a view of the three-dimensional object. Each respective distortion metric may indicate a degree of distortion in a mapping between the respective location in the two-dimensional representation and a corresponding location in a surface texture of the three-dimensional object. The visual representation of the respective distortion metric at one or more of the plurality of locations may be displayed.
摘要翻译： 公开了用于基于失真的掩模生成的方法，系统和计算机可读存储介质。 可以在三维对象的二维表示中的多个位置的每个位置处确定相应的失真度量。 二维表示可以基于三维对象的视图。 每个相应的失真度量可以指示在二维表示中的相应位置与三维对象的表面纹理中的对应位置之间的映射中的失真程度。 可以显示在多个位置中的一个或多个处的相应失真度量的视觉表示。
-
9.发明授权Method and apparatus for computing indirect lighting for global illumination rendering in 3-D computer graphics 有权用于计算3-D计算机图形中的全局照明渲染的间接照明的方法和装置公开(公告)号：US08223148B1
公开(公告)日：2012-07-17
申请号：US12142246
申请日：2008-06-19
CPC分类号： G06T15/506 , G06T15/06
摘要： A method and apparatus for diffuse indirect lighting computation in a scene is described. An irradiance caching algorithm may be implemented in an indirect lighting module that sparsely computes irradiance in the environment and then interpolates irradiance values between these sparsely computed points. The method for diffuse indirect lighting computation may use cosine weighting in determining nearby sample irradiance points to be used in interpolation. If an object detected by a ray is directly overhead, embodiments may assume a significant amount of occlusion or indirect illumination of that surface point, and thus may weight the ray more heavily. If an object is off to the side, and thus at a shallow angle to a normal of the surface point under test, the ray is given less weight. By using cosine weighting, the indirect lighting module tends to space out sample irradiance points better around edges and cracks than conventional techniques.
摘要翻译： 描述了场景中的漫反射间接照明计算的方法和装置。 可以在间接照明模块中实现辐照度缓存算法，该模块稀疏地计算环境中的辐照度，然后在这些稀疏计算点之间内插辐照度值。 散射间接照明计算的方法可以使用余弦加权来确定在插值中使用的附近采样辐照度点。 如果由射线检测到的物体是直接开销的，那么实施例可以承担对该表面点的显着量的遮挡或间接照射，并且因此可以更加重地对射线进行加权。 如果物体偏离侧面，因此与被测试的表面点的法线处于浅的角度，则给予较小的重量。 通过使用余弦加权，间接照明模块倾向于比传统技术更好地围绕边缘和裂缝放置样品辐照点。
-
公开(公告)号：US08873850B2
公开(公告)日：2014-10-28
申请号：US13691718
申请日：2012-11-30
申请人： Aravind Krishnaswamy
发明人： Aravind Krishnaswamy
CPC分类号： G06T5/00 , G06K9/00268 , G06K9/40 , G06K9/46 , G06K9/4647 , G06K9/4661 , G06T5/007 , G06T5/40 , G06T7/0002 , G06T2207/20012 , G06T2207/30168 , G06T2207/30201
摘要： Systems, methods and computer readable media for exposure quality detection are described. In some implementations, a method can include computing an overall image exposure score for an image. The method can also include determining one or more face regions in the image. The method can further include computing a face region exposure score for each face region. The method can also include combining the overall image exposure score and each face region exposure score to generate an exposure quality score for the image.
摘要翻译： 描述了用于曝光质量检测的系统，方法和计算机可读介质。 在一些实现中，一种方法可以包括计算图像的整体图像曝光分数。 该方法还可以包括确定图像中的一个或多个面部区域。 该方法还可以包括计算每个面部区域的面部区域曝光得分。 该方法还可以包括整合图像曝光得分和每个面部区域曝光得分以产生图像的曝光质量分数。
-
-
-
-
-
-
-
-
-
搜索结果
44 条记录 (耗时 0.016 秒)
