-
1.发明授权Real-time capturing and generating viewpoint images and videos with a monoscopic low power mobile device 有权使用单视低功耗移动设备实时捕获和生成视点图像和视频公开(公告)号：US09509980B2
公开(公告)日：2016-11-29
申请号：US14491187
申请日：2014-09-19
Applicant: QUALCOMM INCORPORATED
Inventor： Haohong Wang , Hsiang-Tsun Li , Sharath Manjunath
CPC classification number: H04N13/261 , G06T7/571 , G06T2207/10012 , H04N5/2226 , H04N5/23212 , H04N13/128 , H04N13/161 , H04N13/207 , H04N13/236 , H04N13/271 , H04N13/275
Abstract: A monoscopic low-power mobile device is capable of creating real-time images and videos for multiple viewpoints from a single captured view. The device uses statistics from an autofocusing process to create a block depth map of a single capture view. Artifacts in the block depth map are reduced and an image depth map is created. Alternate views are created from the image depth map using a Z-buffer based surface recover process and a disparity map which is a function of a geometric vision model.
Abstract translation: 单视低功率移动设备能够从单个捕获的视图创建用于多个视点的实时图像和视频。 该设备使用自动对焦过程的统计信息来创建单个捕获视图的块深度图。 减少块深度图中的人工制品，并创建图像深度图。 使用基于Z缓冲的表面恢复过程和作为几何视觉模型的函数的视差图从图像深度图创建替代视图。
-
公开(公告)号：US08797421B2
公开(公告)日：2014-08-05
申请号：US13897669
申请日：2013-05-20
Applicant: QUALCOMM Incorporated
Inventor： Kalin M. Atanassov , Hsiang-Tsun Li , Hau Hwang
CPC classification number: G06T5/50 , G06T3/0068 , G06T2207/10144 , G06T2207/10148 , G06T2207/10152 , G06T2207/20016
Abstract: Systems and methods to selectively combine images are disclosed. In a particular embodiment, an apparatus includes a registration circuit configured to generate a set of motion vector data based on first image data corresponding to a first image and second image data corresponding to a second image. The apparatus includes a combination circuit to selectively combine the first image data and adjusted second image data that corresponds to the second image data adjusted according to the motion vector data. The apparatus further includes a control circuit to control the combination circuit to generate third image data.
Abstract translation: 公开了选择性地组合图像的系统和方法。 在特定实施例中，一种装置包括：配准电路，配置为基于与第一图像对应的第一图像数据和对应于第二图像的第二图像数据生成一组运动矢量数据。 该装置包括组合电路，用于选择性地组合第一图像数据和对应于根据运动矢量数据调整的第二图像数据的经调整的第二图像数据。 该装置还包括控制电路以控制组合电路以产生第三图像数据。
-
3.发明申请REAL-TIME CAPTURING AND GENERATING VIEWPOINT IMAGES AND VIDEOS WITH A MONOSCOPIC LOW POWER MOBILE DEVICE 有权实时捕获和生成具有单声道低功率移动设备的视点图像和视频公开(公告)号：US20150002627A1
公开(公告)日：2015-01-01
申请号：US14491187
申请日：2014-09-19
Applicant: QUALCOMM Incorporated
Inventor： Haohong Wang , Hsiang-Tsun Li , Sharath Manjunath
CPC classification number: H04N13/261 , G06T7/571 , G06T2207/10012 , H04N5/2226 , H04N5/23212 , H04N13/128 , H04N13/161 , H04N13/207 , H04N13/236 , H04N13/271 , H04N13/275
Abstract: A monoscopic low-power mobile device is capable of creating real-time images and videos for multiple viewpoints from a single captured view. The device uses statistics from an autofocusing process to create a block depth map of a single capture view. Artifacts in the block depth map are reduced and an image depth map is created. Alternate views are created from the image depth map using a Z-buffer based surface recover process and a disparity map which is a function of a geometric vision model.
Abstract translation: 单视低功率移动设备能够从单个捕获的视图创建用于多个视点的实时图像和视频。 该设备使用自动对焦过程的统计信息来创建单个捕获视图的块深度图。 减少块深度图中的人工制品，并创建图像深度图。 使用基于Z缓冲的表面恢复过程和作为几何视觉模型的函数的视差图从图像深度图创建替代视图。
-
-
Search Results
3
records
(took 0.01 seconds)
