-
11.发明授权公开(公告)号：US12266383B2
公开(公告)日：2025-04-01
申请号：US18615074
申请日：2024-03-25
Applicant: Intel Corporation
Inventor： Gowri Somanath , Oscar Nestares
IPC: G06T3/00 , G06T3/18 , G06T3/40 , G06T3/4007 , G06T3/4046 , G06T7/246 , G11B27/036 , G11B27/00
Abstract: A mechanism is described for facilitating cinematic space-time view synthesis in computing environments according to one embodiment. A method of embodiments, as described herein, includes capturing, by one or more cameras, multiple images at multiple positions or multiple points in times, where the multiple images represent multiple views of an object or a scene, where the one or more cameras are coupled to one or more processors of a computing device. The method further includes synthesizing, by a neural network, the multiple images into a single image including a middle image of the multiple images and representing an intermediary view of the multiple views.
-
12.发明授权公开(公告)号：US11133033B2
公开(公告)日：2021-09-28
申请号：US16922202
申请日：2020-07-07
Applicant: Intel Corporation
Inventor： Gowri Somanath , Oscar Nestares
IPC: H04N5/77 , G11B27/00 , H04N5/93 , H04N5/92 , G11B27/036 , G06T3/40 , G06T7/246 , G06T3/00 , H04N13/00
Abstract: A mechanism is described for facilitating cinematic space-time view synthesis in computing environments according to one embodiment. A method of embodiments, as described herein, includes capturing, by one or more cameras, multiple images at multiple positions or multiple points in times, where the multiple images represent multiple views of an object or a scene, where the one or more cameras are coupled to one or more processors of a computing device. The method further includes synthesizing, by a neural network, the multiple images into a single image including a middle image of the multiple images and representing an intermediary view of the multiple views.
-
公开(公告)号：US20200345317A1
公开(公告)日：2020-11-05
申请号：US16877135
申请日：2020-05-18
Applicant: INTEL CORPORATION
Inventor： Gowri Somanath , Karthik Natarajan
Abstract: An apparatus, method, and machine-readable medium for health monitoring and response are described herein. The apparatus includes a processor and a number of sensors configured to collect data corresponding to a user of the device. The apparatus also includes a health monitoring and response application, at least partially including hardware logic. The hardware logic of the health monitoring and response application is to test the data collected by any of the sensors to match the collected data with a predetermined health condition, determine a current health condition of the user based on the predetermined health condition that matches the collected data, and automatically perform an action based on the current health condition of the user.
-
公开(公告)号：US20170372479A1
公开(公告)日：2017-12-28
申请号：US15190784
申请日：2016-06-23
Applicant: INTEL CORPORATION
Inventor： Gowri Somanath , Jiajie Yao , Yong Jiang
CPC classification number: G06T7/11 , G06T7/136 , G06T7/143 , G06T7/174 , G06T2207/10016 , G06T2207/10024 , G06T2207/10028 , G06T2207/20112
Abstract: Techniques are provided for segmentation of objects, in videos comprising a sequence of color and depth image frames. A methodology implementing the techniques according to an embodiment includes receiving image frames, including an initial reference frame, and receiving a mask to outline a region in the reference frame that contains the object to be segmented. The method also includes calculating Gaussian mixture models associated with both the masked region and a background region external to the masked region. The method further includes segmenting the object from a current frame based on a modelling of the pixels within an active area of the current frame as a Markov Random Field of nodes for cost minimization. The costs are based in part on the Gaussian mixture models. The active area is based on the segmentation of a previous frame and on an estimation of optical flow between the previous frame and the current frame.
-
公开(公告)号：US09628695B2
公开(公告)日：2017-04-18
申请号：US14660848
申请日：2015-03-17
Applicant: INTEL CORPORATION
Inventor： Gowri Somanath , Oscar Nestares , Kalpana Seshadrinathan , Yi Wu
CPC classification number: H04N5/23212 , G03B13/36 , H04N13/246 , H04N13/25 , H04N17/002
Abstract: A system, article, and method of lens shift correction for a camera array.
-
Patent Agency Ranking
公开(公告)号：US09547907B2
公开(公告)日：2017-01-17
申请号：US14570941
申请日：2014-12-15
Applicant: Intel Corporation
Inventor： Gowri Somanath
IPC: G06T7/00
CPC classification number: G06T7/11 , G06T7/143 , G06T7/194 , G06T2207/10028 , G06T2207/20072
Abstract: Image segmentation utilizing 3D image data. A plurality of pixels of an image frame may be segmented based at least on a function of pixel color and a pixel depth over the spatial positions within the image frame. A graph-cut technique may be utilized to optimize a data cost and smoothness cost in which at least the data cost function includes a component that is a dependent on a depth associated with a given pixel in the frame. In further embodiments, both the data cost and smoothness functions are dependent on a color and a depth associated with each pixel. Components of at least the data cost function may be weighted for each pixel to arrive at most likely segments. Segmentation may be further predicated on a pre-segmentation label assigned based at least on a 3D spatial position clusters.
Abstract translation: 使用3D图像数据的图像分割。 可以至少基于像素颜色的函数和图像帧内的空间位置上的像素深度来分割图像帧的多个像素。 可以使用图形切割技术来优化数据成本和平滑度成本，其中至少数据成本函数包括依赖于与帧中的给定像素相关联的深度的分量。 在另外的实施例中，数据成本和平滑度函数均取决于与每个像素相关联的颜色和深度。 可以对每个像素加权至少数据成本函数的组件以到达最可能的段。 分割可以进一步基于至少基于3D空间位置聚类分配的预分割标签。
-
17.发明授权公开(公告)号：US11972780B2
公开(公告)日：2024-04-30
申请号：US17486476
申请日：2021-09-27
Applicant: Intel Corporation
Inventor： Gowri Somanath , Oscar Nestares
IPC: G06T3/00 , G06T3/40 , G06T3/4007 , G06T3/4046 , G06T7/246 , G06T13/00 , G11B27/036 , G11B27/00
CPC classification number: G11B27/036 , G06T3/0093 , G06T3/4007 , G06T3/4046 , G06T7/246 , G06T2207/10016 , G06T2207/20081 , G06T2207/20084 , G06T2207/20221
Abstract: A mechanism is described for facilitating cinematic space-time view synthesis in computing environments according to one embodiment. A method of embodiments, as described herein, includes capturing, by one or more cameras, multiple images at multiple positions or multiple points in times, where the multiple images represent multiple views of an object or a scene, where the one or more cameras are coupled to one or more processors of a computing device. The method further includes synthesizing, by a neural network, the multiple images into a single image including a middle image of the multiple images and representing an intermediary view of the multiple views.
-
18.发明申请公开(公告)号：US20220013148A1
公开(公告)日：2022-01-13
申请号：US17486476
申请日：2021-09-27
Applicant: Intel Corporation
Inventor： Gowri Somanath , Oscar Nestares
IPC: G11B27/036 , G06T3/40 , G06T7/246 , G06T3/00
Abstract: A mechanism is described for facilitating cinematic space-time view synthesis in computing environments according to one embodiment. A method of embodiments, as described herein, includes capturing, by one or more cameras, multiple images at multiple positions or multiple points in times, where the multiple images represent multiple views of an object or a scene, where the one or more cameras are coupled to one or more processors of a computing device. The method further includes synthesizing, by a neural network, the multiple images into a single image including a middle image of the multiple images and representing an intermediary view of the multiple views.
-
19.发明申请公开(公告)号：US20210056998A1
公开(公告)日：2021-02-25
申请号：US16922202
申请日：2020-07-07
Applicant: Intel Corporation
Inventor： Gowri Somanath , Oscar Nestares
IPC: G11B27/036 , G06T3/40 , G06T7/246 , G06T3/00
Abstract: A mechanism is described for facilitating cinematic space-time view synthesis in computing environments according to one embodiment. A method of embodiments, as described herein, includes capturing, by one or more cameras, multiple images at multiple positions or multiple points in times, where the multiple images represent multiple views of an object or a scene, where the one or more cameras are coupled to one or more processors of a computing device. The method further includes synthesizing, by a neural network, the multiple images into a single image including a middle image of the multiple images and representing an intermediary view of the multiple views.
-
20.发明授权公开(公告)号：US10706890B2
公开(公告)日：2020-07-07
申请号：US15685213
申请日：2017-08-24
Applicant: Intel Corporation
Inventor： Gowri Somanath , Oscar Nestares
IPC: H04N5/77 , G11B27/00 , H04N5/93 , G11B27/036 , G06T3/40 , G06T7/246 , G06T3/00 , H04N5/92 , H04N13/00
Abstract: A mechanism is described for facilitating cinematic space-time view synthesis in computing environments according to one embodiment. A method of embodiments, as described herein, includes capturing, by one or more cameras, multiple images at multiple positions or multiple points in times, where the multiple images represent multiple views of an object or a scene, where the one or more cameras are coupled to one or more processors of a computing device. The method further includes synthesizing, by a neural network, the multiple images into a single image including a middle image of the multiple images and representing an intermediary view of the multiple views.
-
-
-
-
-
-
-
-
-
Search Results
23
records
(took 0.019 seconds)
