-
公开(公告)号：US09892496B2
公开(公告)日：2018-02-13
申请号：US15344501
申请日：2016-11-04
Applicant: Google Inc.
Inventor： Jonathan Tilton Barron , Benjamin Michael Poole
CPC classification number: G06T5/20 , G06K9/42 , G06K9/4652 , G06K9/469 , G06K9/6215 , G06T3/4076 , G06T5/003 , G06T5/50 , G06T2207/10024 , G06T2207/20028
Abstract: Example embodiments may allow for the efficient, edge-preserving filtering, upsampling, or other processing of image data with respect to a reference image. A cost-minimization problem to generate an output image from the input array is mapped onto regularly-spaced vertices in a multidimensional vertex space. This mapping is based on an association between pixels of the reference image and the vertices, and between elements of the input array and the pixels of the reference image. The problem is them solved to determine vertex disparity values for each of the vertices. Pixels of the output image can be determined based on determined vertex disparity values for respective one or more vertices associated with each of the pixels. This fast, efficient image processing method can be used to enable edge-preserving image upsampling, image colorization, semantic segmentation of image contents, image filtering or de-noising, or other applications.
-
公开(公告)号：US09762893B2
公开(公告)日：2017-09-12
申请号：US14961102
申请日：2015-12-07
Applicant: Google Inc.
Inventor： Jonathan Tilton Barron , Stephen Joseph DiVerdi , Ryan Geiss
CPC classification number: H04N13/239 , G06K9/6204 , G06T5/002 , G06T5/007 , G06T5/10 , G06T7/269 , G06T7/292 , G06T7/30 , G06T7/38 , G06T2207/10012 , G06T2207/10024 , G06T2207/20208 , H04N5/2355 , H04N9/09 , H04N13/271 , H04N2013/0081 , H04N2013/0088
Abstract: The present disclosure relates to methods and systems that may improve and/or modify images captured using multiscopic image capture systems. In an example embodiment, burst image data is captured via a multiscopic image capture system. The burst image data may include at least one image pair. The at least one image pair is aligned based on at least one rectifying homography function. The at least one aligned image pair is warped based on a stereo disparity between the respective images of the image pair. The warped and aligned images are then stacked and a denoising algorithm is applied. Optionally, a high dynamic range algorithm may be applied to at least one output image of the aligned, warped, and denoised images.
-
公开(公告)号：US20170132769A1
公开(公告)日：2017-05-11
申请号：US15344501
申请日：2016-11-04
Applicant: Google Inc.
Inventor： Jonathan Tilton Barron , Ben Poole
CPC classification number: G06T5/20 , G06K9/42 , G06K9/4652 , G06K9/469 , G06K9/6215 , G06T3/4076 , G06T5/003 , G06T5/50 , G06T2207/10024 , G06T2207/20028
Abstract: Example embodiments may allow for the efficient, edge-preserving filtering, upsampling, or other processing of image data with respect to a reference image. A cost-minimization problem to generate an output image from the input array is mapped onto regularly-spaced vertices in a multidimensional vertex space. This mapping is based on an association between pixels of the reference image and the vertices, and between elements of the input array and the pixels of the reference image. The problem is them solved to determine vertex disparity values for each of the vertices. Pixels of the output image can be determined based on determined vertex disparity values for respective one or more vertices associated with each of the pixels. This fast, efficient image processing method can be used to enable edge-preserving image upsampling, image colorization, semantic segmentation of image contents, image filtering or de-noising, or other applications.
-
Patent Agency Ranking
公开(公告)号：US20170163966A1
公开(公告)日：2017-06-08
申请号：US14961102
申请日：2015-12-07
Applicant: Google Inc.
Inventor： Jonathan Tilton Barron , Stephen Joseph DiVerdi , Ryan Geiss
CPC classification number: H04N13/239 , G06K9/6204 , G06T5/002 , G06T5/007 , G06T5/10 , G06T7/269 , G06T7/292 , G06T7/30 , G06T7/38 , G06T2207/10012 , G06T2207/10024 , G06T2207/20208 , H04N5/2355 , H04N9/09 , H04N13/271 , H04N2013/0081 , H04N2013/0088
Abstract: The present disclosure relates to methods and systems that may improve and/or modify images captured using multiscopic image capture systems. In an example embodiment, burst image data is captured via a multiscopic image capture system. The burst image data may include at least one image pair. The at least one image pair is aligned based on at least one rectifying homography function. The at least one aligned image pair is warped based on a stereo disparity between the respective images of the image pair. The warped and aligned images are then stacked and a denoising algorithm is applied. Optionally, a high dynamic range algorithm may be applied to at least one output image of the aligned, warped, and denoised images.
-
公开(公告)号：US09076033B1
公开(公告)日：2015-07-07
申请号：US13630537
申请日：2012-09-28
Applicant: Google Inc.
Inventor： Jonathan Tilton Barron , Marc Stewart Levoy , Samuel William Hasinoff
CPC classification number: G06K9/00355 , G06F1/163 , G06F3/005 , G06F3/011 , G06F3/017 , G06F3/0304 , G06F3/04842 , G06K9/00671 , G06K9/2081 , H04N5/2257 , H04N5/23216 , H04N5/23293
Abstract: Embodiments described herein may help a computing device, such as a head-mountable device (HMD), to capture and process images in response to a user placing their hands in, and then withdrawing their hands from, a frame formation. For example, an HMD may analyze image data from a point-of-view camera on the HMD, and detect when a wearer holds their hands in front of their face to frame a subject in the wearer's field of view. Further, the HMD may detect when the wearer withdraws their hands from such a frame formation and responsively capture an image. Further, the HMD may determine a selection area that is being framed, within the wearer's field of view, by the frame formation. The HMD may then process the captured image based on the frame formation, such as by cropping, white-balancing, and/or adjusting exposure.
Abstract translation: 本文描述的实施例可以帮助计算设备，例如可头戴式设备（HMD），以响应于用户将他们的手放置在框架结构中，然后从框架结构中取出他们的手来捕获和处理图像。 例如，HMD可以分析来自HMD上的观察点相机的图像数据，并且检测佩戴者在佩戴者的视野内何时将手握在脸部的前方以构图被摄体。 此外，HMD可以检测穿戴者何时从这样的框架结构中撤回他们的手并且响应地捕获图像。 此外，HMD可以通过框架形成来确定正在框架的选择区域，在佩戴者的视野范围内。 然后，HMD可以基于帧形成处理捕获的图像，例如通过裁剪，白平衡和/或调整曝光。
-
公开(公告)号：US09571819B1
公开(公告)日：2017-02-14
申请号：US14487387
申请日：2014-09-16
Applicant: Google Inc.
Inventor： Jonathan Tilton Barron
IPC: H04N13/02
CPC classification number: H04N13/239 , H04N13/128 , H04N13/296 , H04N2013/0077 , H04N2013/0081
Abstract: Example embodiments may allow for the efficient determination of disparity information for a stereo image pair by embedding pixels of the image pair in a multidimensional dimensional vertex space. Regularly-spaced vertices in the vertex space are associated with pixels of the stereo image pair and disparity loss functions are determined for each of the vertices based on disparity loss functions of the associated pixels. The determined vertex-disparity loss functions can be used to determine vertex disparity values for each of the vertices. Disparity values for pixels of the stereo image pair can be determined based on determined vertex disparity values for respective one or more vertices associated with each of the pixels. The determined pixel disparity values can be used to enable depth-selective image processing, determination of pixel depth maps, mapping and/or navigation of an environment, human-computer interfacing, biometrics, augmented reality, or other applications.
Abstract translation: 示例性实施例可以通过将图像对的像素嵌入到多维尺寸顶点空间中来有效地确定立体图像对的视差信息。 顶点空间中的经常间隔的顶点与立体图像对的像素相关联，并且基于相关像素的视差损失函数为每个顶点确定视差损失函数。 确定的顶点 - 视差损失函数可用于确定每个顶点的顶点视差值。 可以基于与每个像素相关联的相应一个或多个顶点的确定的顶点视差值来确定立体图像对的像素的视差值。 确定的像素差异值可用于实现深度选择性图像处理，像素深度图的确定，环境的映射和/或导航，人机界面，生物特征，增强现实或其他应用。
-
公开(公告)号：US20170347088A1
公开(公告)日：2017-11-30
申请号：US15676145
申请日：2017-08-14
Applicant: Google Inc.
Inventor： Jonathan Tilton Barron , Stephen Joseph DiVerdi , Ryan Geiss
CPC classification number: H04N13/239 , G06K9/6204 , G06T5/002 , G06T5/007 , G06T5/10 , G06T7/269 , G06T7/292 , G06T7/30 , G06T7/38 , G06T2207/10012 , G06T2207/10024 , G06T2207/20208 , H04N5/2355 , H04N9/09 , H04N13/271 , H04N2013/0081 , H04N2013/0088
Abstract: The present disclosure relates to methods and systems that may improve and/or modify images captured using multiscopic image capture systems. In an example embodiment, burst image data is captured via a multiscopic image capture system. The burst image data may include at least one image pair. The at least one image pair is aligned based on at least one rectifying homography function. The at least one aligned image pair is warped based on a stereo disparity between the respective images of the image pair. The warped and aligned images are then stacked and a denoising algorithm is applied. Optionally, a high dynamic range algorithm may be applied to at least one output image of the aligned, warped, and denoised images.
-
公开(公告)号：US09736451B1
公开(公告)日：2017-08-15
申请号：US15394314
申请日：2016-12-29
Applicant: Google Inc.
Inventor： Jonathan Tilton Barron
CPC classification number: H04N13/239 , H04N13/128 , H04N13/296 , H04N2013/0077 , H04N2013/0081
Abstract: Example embodiments may allow for the efficient determination of disparity information for a stereo image pair by embedding pixels of the image pair in a multidimensional dimensional vertex space. Regularly-spaced vertices in the vertex space are associated with pixels of the stereo image pair and disparity loss functions are determined for each of the vertices based on disparity loss functions of the associated pixels. The determined vertex-disparity loss functions can be used to determine vertex disparity values for each of the vertices. Disparity values for pixels of the stereo image pair can be determined based on determined vertex disparity values for respective one or more vertices associated with each of the pixels. The determined pixel disparity values can be used to enable depth-selective image processing, determination of pixel depth maps, mapping and/or navigation of an environment, human-computer interfacing, biometrics, augmented reality, or other applications.
-
-
-
-
-
-
-
Search Results
8
records
(took 0.014 seconds)
