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

US08350850B2 Using photo collections for three dimensional modeling 有权
公开(公告)号：US08350850B2
公开(公告)日：2013-01-08
申请号：US12059794
申请日：2008-03-31
申请人： Drew Steedly , Richard Szeliski , Sudipta Sinha , Maneesh Agrawala
发明人： Drew Steedly , Richard Szeliski , Sudipta Sinha , Maneesh Agrawala
IPC分类号： G06T17/00 , G06T15/00
CPC分类号： G06T17/00 , G06T7/536 , G06T7/564 , G06T15/205 , G06T2200/08 , G06T2207/10016
摘要： A collection of photos and a three-dimensional reconstruction of the photos are used to construct and texture a mesh model. In one embodiment, a first digital image of a first view of a real world scene is analyzed to identify lines in the first view. Among the lines, parallel lines are identified. A three-dimensional vanishing direction in a three-dimensional space is determined based on the parallel lines and an orientation of the digital image in the three-dimensional space. A plane is automatically generated by fitting the plane to the vanishing direction. A rendering of a three-dimensional model with the plane is displayed. Three-dimensional points corresponding to features common to the photos may be used to constrain the plane. The photos may be projected onto the model to provide visual feedback when editing the plane. Furthermore, the photos may be used to texture the model.

2. 发明申请

US20090244062A1 USING PHOTO COLLECTIONS FOR THREE DIMENSIONAL MODELING 有权
标题翻译：使用三维建模的照片集
公开(公告)号：US20090244062A1
公开(公告)日：2009-10-01
申请号：US12059794
申请日：2008-03-31
申请人： Drew Steedly , Richard Szeliski , Sudipta Sinha , Maneesh Agrawala
发明人： Drew Steedly , Richard Szeliski , Sudipta Sinha , Maneesh Agrawala
IPC分类号： G06T17/00 , G09G5/00
CPC分类号： G06T17/00 , G06T7/536 , G06T7/564 , G06T15/205 , G06T2200/08 , G06T2207/10016
摘要： A collection of photos and a three-dimensional reconstruction of the photos are used to construct and texture a mesh model. In one embodiment, a first digital image of a first view of a real world scene is analyzed to identify lines in the first view. Among the lines, parallel lines are identified. A three-dimensional vanishing direction in a three-dimensional space is determined based on the parallel lines and an orientation of the digital image in the three-dimensional space. A plane is automatically generated by fitting the plane to the vanishing direction. A rendering of a three-dimensional model with the plane is displayed. Three-dimensional points corresponding to features common to the photos may be used to constrain the plane. The photos may be projected onto the model to provide visual feedback when editing the plane. Furthermore, the photos may be used to texture the model.
摘要翻译：使用照片的集合和照片的三维重建来构造和纹理网格模型。在一个实施例中，分析现实世界场景的第一视图的第一数字图像以识别第一视图中的线。在行中，确定了平行线。基于三维空间中的数字图像的平行线和取向来确定三维空间中的三维消失方向。通过将平面装配到消失方向，自动生成平面。显示用平面渲染三维模型。对应于照片共同特征的三维点可以用于约束平面。照片可以投影到模型上，以便在编辑飞机时提供视觉反馈。此外，照片可以用于纹理模型。

3. 发明授权

US07499586B2 Photographing big things 有权
标题翻译：拍摄大件事情
公开(公告)号：US07499586B2
公开(公告)日：2009-03-03
申请号：US11323241
申请日：2005-12-30
申请人： Aseem O. Agarwala , Maneesh Agrawala , Michael F. Cohen , David H. Salesin , Richard Szeliski
发明人： Aseem O. Agarwala , Maneesh Agrawala , Michael F. Cohen , David H. Salesin , Richard Szeliski
IPC分类号： G06K9/00 , G06K9/36 , G09G5/00
CPC分类号： G06T3/4038 , Y10S707/99933
摘要： The subject application provides an architecture that facilitates producing a single image that can visualize a scene too large to depict from any single perspective view. These images can be stitched together on a 2-dimensional picture surface to form a multi-perspective image of the entire extent of the scene depicted by the input images. Where the respective images overlap, an objective function can be employed to determine where to make a transition between one image and the next. The objective function can employ a data cost and a seam cost to make this determination.
摘要翻译：主题应用程序提供了一种便于生成可以使场景过大可视化的单个图像以便从任何单一透视图进行描绘的架构。这些图像可以在二维图像表面上缝合在一起以形成由输入图像描绘的场景的整个范围的多视角图像。在各个图像重叠的地方，可以采用目标函数来确定在一个图像和下一个图像之间进行转换的位置。目标函数可以采用数据成本和接缝成本来做出这一决定。

4. 发明申请

US20070076016A1 Photographing big things 有权
标题翻译：拍摄大件事情
公开(公告)号：US20070076016A1
公开(公告)日：2007-04-05
申请号：US11323241
申请日：2005-12-30
申请人： Aseem Agarwala , Maneesh Agrawala , Michael Cohen , David Salesin , Richard Szeliski
发明人： Aseem Agarwala , Maneesh Agrawala , Michael Cohen , David Salesin , Richard Szeliski
IPC分类号： G09G5/00
CPC分类号： G06T3/4038 , Y10S707/99933
摘要： The claimed subject matter can provide an architecture that facilitates producing a single image that can visualize a scene too large to depict from any single perspective view. These images can be stitched together on a 2-dimensional picture surface to form a multi-perspective image of the entire extent of the scene depicted by the input images. Where the respective images overlap, an objective function can be employed to determine where to make a transition between one image and the next. The objective function can employ a data cost and a seam cost to make this determination.
摘要翻译：所要求保护的主题可以提供便于产生可以使场景过大可视化的单个图像的架构，从而不能从任何单个透视图描绘。这些图像可以在二维图像表面上缝合在一起以形成由输入图像描绘的场景的整个范围的多视角图像。在各个图像重叠的地方，可以采用目标函数来确定在一个图像和下一个图像之间进行转换的位置。目标函数可以采用数据成本和接缝成本来做出这一决定。

5. 发明授权

US07457477B2 Digital photography with flash/no flash extension 失效
标题翻译：带闪光灯/无闪光灯扩展的数码摄影
公开(公告)号：US07457477B2
公开(公告)日：2008-11-25
申请号：US10885259
申请日：2004-07-06
申请人： Georg F. Petschnigg , Richard Szeliski , Michael F. Cohen , Hugues Hoppe , Maneesh Agrawala
发明人： Georg F. Petschnigg , Richard Szeliski , Michael F. Cohen , Hugues Hoppe , Maneesh Agrawala
IPC分类号： H04N5/222 , G06K9/00 , G06K9/62 , G06K9/40
CPC分类号： G06T5/50
摘要： A system and method for improving digital flash photographs. The present invention is a technique that significantly improves low-light imaging by giving the end-user all the advantages of flash photography without producing the jarring look. The invention uses an image pair—one taken with flash the other without—to remove noise from the ambient image, sharpen the ambient image using detail from the flash image, correct for color, and remove red-eye.
摘要翻译：一种用于改进数码闪光照片的系统和方法。本发明是一种技术，通过给终端用户提供闪光摄影的所有优点，而不会产生刺耳的外观，显着地改善了低光成像。本发明使用图像对 - 其他闪光拍摄而不是从环境图像中去除噪声，使用来自闪光图像的细节来锐化环境图像，校正颜色并去除红眼。

6. 发明申请

US20060008171A1 Digital photography with flash/no flash extension 失效
标题翻译：带闪光灯/无闪光灯扩展的数码摄影
公开(公告)号：US20060008171A1
公开(公告)日：2006-01-12
申请号：US10885259
申请日：2004-07-06
申请人： Georg Petschnigg , Richard Szeliski , Michael Cohen , Hugues Hoppe , Maneesh Agrawala
发明人： Georg Petschnigg , Richard Szeliski , Michael Cohen , Hugues Hoppe , Maneesh Agrawala
IPC分类号： G06K9/40
CPC分类号： G06T5/50
摘要： A system and method for improving digital flash photographs. The present invention is a technique that significantly improves low-light imaging by giving the end-user all the advantages of flash photography without producing the jarring look. The invention uses an image pair—one taken with flash the other without—to remove noise from the ambient image, sharpen the ambient image using detail from the flash image, correct for color, and remove red-eye.
摘要翻译：一种用于改进数码闪光照片的系统和方法。本发明是一种技术，通过给终端用户提供闪光摄影的所有优点，而不会产生刺耳的外观，显着地改善了低光成像。本发明使用图像对 - 其他闪光拍摄而不是从环境图像中去除噪声，使用来自闪光图像的细节来锐化环境图像，校正颜色并去除红眼。

7. 发明授权

US07437279B2 System and method for abstracting and visualizing a route map 失效
标题翻译：用于抽象和可视化路线图的系统和方法
公开(公告)号：US07437279B2
公开(公告)日：2008-10-14
申请号：US11073399
申请日：2005-03-04
申请人： Maneesh Agrawala , Chris Stolte
发明人： Maneesh Agrawala , Chris Stolte
IPC分类号： G06G7/48 , G06F3/00
CPC分类号： G06T17/05 , G01C21/367 , G01C21/3673 , G06T11/206 , G06T11/60
摘要： A system and method for making computer-generated maps includes a different scale factor for each road in a route. The scale factors are used to optimize the route map against a target function that considers factors such as the number of false intersections in the route and the number of roads falling below a minimum length threshold. A refinement technique such as simulated annealing is used to find a solution to the target function. Each road in the scaled map is rendered to provide a finished product having the appearance of a hand-drawn map. The finished product includes context roads that intersect the main route but are not part of the main route. Furthermore, the hand-drawn map is optimized to the characteristics of the viewport used to visualize the map.
摘要翻译：用于制作计算机生成的地图的系统和方法包括路线中每条道路的不同比例因子。比例因子用于针对目标函数优化路线图，该目标函数考虑到诸如路线中的错误交叉点数量和低于最小长度阈值的道路数量等因素。使用诸如模拟退火的细化技术来找到目标函数的解。缩放地图中的每个道路被渲染以提供具有手绘地图的外观的成品。成品包括与主路线相交但不属于主路线的上下文道路。此外，手绘地图针对用于可视化地图的视口的特征进行了优化。

8. 发明申请

US20070242036A1 Dual control data entry 审中-公开
标题翻译：双控制数据输入
公开(公告)号：US20070242036A1
公开(公告)日：2007-10-18
申请号：US11405224
申请日：2006-04-17
申请人： Andrew Wilson , Maneesh Agrawala
发明人： Andrew Wilson , Maneesh Agrawala
IPC分类号： G09G5/00
CPC分类号： A63F13/42 , A63F13/00 , A63F13/22 , A63F2300/6045 , G06F3/0236 , G06F3/0346
摘要： Alphanumeric input is achieved using a handset having a limited number of controls but at least two controls—a first control and a second control. A key layout is rendered on a display. The key layout includes two parts—a first part and a second part. One of the two controls of the handset is associated with one of the two parts of the key layout such that characters within that part are selected with the one control. Likewise, the other of the two controls is associated with the other of the two parts of the key layout such that characters within the other part are selected with the other control.
摘要翻译：使用具有有限数量的控制但至少两个控制的手持机实现字母数字输入 - 第一控制和第二控制。关键布局在显示器上呈现。关键布局包括两部分 - 第一部分和第二部分。手机的两个控件中的一个与键布局的两个部分中的一个相关联，使得该部分中的字符被一个控制选择。类似地，两个控件中的另一个与键布局的两个部分中的另一个相关联，使得另一部分中的字符与另一个控件一起被选择。

9. 发明申请

US20070112507A1 SCHEMATIC DESTINATION MAPS 有权
标题翻译：原型目的地
公开(公告)号：US20070112507A1
公开(公告)日：2007-05-17
申请号：US11420550
申请日：2006-05-26
申请人： David Bargeron , Maneesh Agrawala , David Salesin
发明人： David Bargeron , Maneesh Agrawala , David Salesin
IPC分类号： G01C21/00
CPC分类号： G01C21/3667 , G09B29/106
摘要： The claimed subject matter provides a system and/or a method that facilitates automatically producing an enhanced schematic destination map to provide directions to a destination related to geography. An interface component can receive at least one geographic destination. A map generator can automatically create an enhanced schematic destination map utilizing a hierarchy of road sets to provide at least one route including at least one road to the geographic destination.
摘要翻译：所要求保护的主题提供了一种系统和/或方法，其有助于自动产生增强的示意图目的地地图，以向与地理相关的目的地提供指示。接口组件可以接收至少一个地理目的地。地图生成器可以使用道路集的层级来自动创建增强的示意图目的地地图，以提供至少一条包括至少一条通往地理目的地的道路的路线。

10. 发明申请

US20060200759A1 Techniques for generating the layout of visual content 审中-公开
标题翻译：生成视觉内容布局的技术
公开(公告)号：US20060200759A1
公开(公告)日：2006-09-07
申请号：US11072747
申请日：2005-03-04
申请人： Maneesh Agrawala , Adam Eversole , Daniel Vogel , Charles Jacobs , David Salesin
发明人： Maneesh Agrawala , Adam Eversole , Daniel Vogel , Charles Jacobs , David Salesin
IPC分类号： G06F17/00
CPC分类号： G06F17/211
摘要： Systems and methods comprising a general purpose framework to facilitate automated layout are provided. Such systems and methods can be utilized to automatically generate visual content over a wide range of domains. One example of a framework comprises a set of general purpose layout components adjustable to a plurality of domains. The general purpose layout components facilitate the automated arrangement of visual elements according to a plurality of style rules. One example of a method performed utilizing one or more elements of a general purpose adaptable layout framework comprises quantifying at least one aesthetic quality of a depiction in relation to one or more non-mandatory objectives to produce a quantified aesthetic quality, and automatically optimizing the quantified aesthetic quality to produce an enhanced depiction.
摘要翻译：提供了包括用于促进自动布局的通用框架的系统和方法。这样的系统和方法可以用于在广泛的域上自动产生视觉内容。框架的一个示例包括可调整到多个域的一组通用布局组件。通用布局组件便于根据多种风格规则自动排列视觉元素。使用通用可适应布局框架的一个或多个元件执行的方法的一个示例包括相对于一个或多个非强制性目标量化至少一个描述的美学质量以产生量化的美学品质，并自动优化量化的美学质量产生增强的描绘。

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