-
公开(公告)号：US10440497B2
公开(公告)日：2019-10-08
申请号：US15815763
申请日：2017-11-17
Applicant: Intel Corporation
Inventor： Raghavendra Rao R , Przemyslaw Maziewski , Adam Kupryjanow , Anbumani Subramanian
Abstract: A mechanism is described for facilitating multi-modal dereverberation in far-field audio systems according to one embodiment. A method of embodiments, as described herein, includes performing geometry estimation of a geographical space based on visuals of the space received from one or more cameras of a computing device. The method may further include computing reverberation time based on the geometry estimation that is further based on the visuals, and computing and applying dereverberation based on the reverberation time.
-
公开(公告)号：US20160142673A1
公开(公告)日：2016-05-19
申请号：US14543012
申请日：2014-11-17
Applicant: Intel Corporation
Inventor： Raghavendra R. Rao , Anbumani Subramanian
CPC classification number: G06K9/0061 , G06K9/00604 , H04N7/144 , H04N2007/145
Abstract: Techniques are disclosed for improving perceived eye-contact in video communications on personal communication devices that have a camera positioned offset slightly away from a display screen, such as found in tablets, mobile phones, laptops, desktops ultrabooks, all-in-ones, and the like. A three-dimensional mesh, such as a point cloud, may be created from an image and depth information that is captured of the user. A viewing direction of is determined by assessing the three-dimensional mesh and the mesh is rotated to minimize the angle between the viewing direction and a line of sight between the user's eyes and the camera.
Abstract translation: 公开了一种技术，用于改善个人通信设备上的视频通信中的视觉接触，所述个人通信设备具有位置偏离显示屏稍微偏离的照相机，例如在平板电脑，移动电话，膝上型计算机，台式机超大型机，一体式和 类似。 可以从用户捕获的图像和深度信息创建诸如点云的三维网格。 通过评估三维网格来确定观察方向，并旋转网格以最小化观看方向与用户的眼睛和相机之间的视线之间的角度。
-
公开(公告)号：US20190028829A1
公开(公告)日：2019-01-24
申请号：US15815763
申请日：2017-11-17
Applicant: Intel Corporation
Inventor： Raghavendra Rao R , Przemyslaw Maziewski , Adam Kupryjanow , Anbumani Subramanian
CPC classification number: H04S7/305 , G06T7/62 , G06T17/00 , G06T2207/10004 , H04S7/303
Abstract: A mechanism is described for facilitating multi-modal dereverberation in far-field audio systems according to one embodiment. A method of embodiments, as described herein, includes performing geometry estimation of a geographical space based on visuals of the space received from one or more cameras of a computing device. The method may further include computing reverberation time based on the geometry estimation that is further based on the visuals, and computing and applying dereverberation based on the reverberation time.
-
公开(公告)号：US09626564B2
公开(公告)日：2017-04-18
申请号：US14543012
申请日：2014-11-17
Applicant: Intel Corporation
Inventor： Raghavendra R. Rao , Anbumani Subramanian
CPC classification number: G06K9/0061 , G06K9/00604 , H04N7/144 , H04N2007/145
Abstract: Techniques are disclosed for improving perceived eye-contact in video communications on personal communication devices that have a camera positioned offset slightly away from a display screen, such as found in tablets, mobile phones, laptops, desktops ultrabooks, all-in-ones, and the like. A three-dimensional mesh, such as a point cloud, may be created from an image and depth information that is captured of the user. A viewing direction of is determined by assessing the three-dimensional mesh and the mesh is rotated to minimize the angle between the viewing direction and a line of sight between the user's eyes and the camera.
-
-
-
Search Results
4
records
(took 0.011 seconds)
