-
公开(公告)号:US20220415030A1
公开(公告)日:2022-12-29
申请号:US17778085
申请日:2019-11-19
Applicant: Tingbo HOU , Jianing WEI , Adel AHMADYAN , Matthias GRUNDMANN , Google LLC
Inventor: Tingbo Hou , Jianing Wei , Adel Ahmadyan , Matthias Grundmann
IPC: G06V10/774 , G06V20/64
Abstract: The present disclosure is directed to systems and methods for generating synthetic training data using augmented reality (AR) techniques. For example, images of a scene can be used to generate a three-dimensional mapping of the scene. The three-dimensional mapping may be associated with the images to indicate locations for positioning a virtual object. Using an AR rendering engine, implementations can generate an and orientation. The augmented image can then be stored in a machine learning dataset and associated with a label based on aspects of the virtual object.
-
公开(公告)号:US20110102642A1
公开(公告)日:2011-05-05
申请号:US12612135
申请日:2009-11-04
Applicant: Sen Wang , Tingbo Hou , Rodney L. Miller
Inventor: Sen Wang , Tingbo Hou , Rodney L. Miller
CPC classification number: H04N5/23248 , G06T5/003 , G06T5/50 , G06T2207/20201 , H04N5/23277
Abstract: A method for determining a deblurred image comprising: receiving a blurred image of a scene; receiving a blur kernel; initializing a candidate deblurred image; determining a plurality of differential images representing differences between neighboring pixels in the candidate deblurred image; determining a combined differential image by combining the differential images; repeatedly updating the candidate deblurred image responsive to the blurred image, the blur kernel, the candidate deblurred image and the combined differential image until a convergence criterion is satisfied; and storing the final candidate deblurred image in a processor-accessible memory system.
Abstract translation: 一种用于确定去模糊图像的方法,包括:接收场景的模糊图像; 接收模糊内核; 初始化候选的未模糊图像; 确定表示候选去模糊图像中的相邻像素之间的差的多个差分图像; 通过组合差分图像来确定组合差分图像; 响应于模糊图像,模糊核心,候选去模糊图像和组合差分图像反复更新候选去模糊图像,直到满足收敛标准; 以及将最终的候选去模糊图像存储在处理器可访问的存储器系统中。
-
公开(公告)号:US20110090352A1
公开(公告)日:2011-04-21
申请号:US12580569
申请日:2009-10-16
Applicant: Sen Wang , Tingbo Hou , Rodney L. Miller
Inventor: Sen Wang , Tingbo Hou , Rodney L. Miller
CPC classification number: H04N5/23248 , G06T5/003 , G06T5/50 , G06T2207/10016 , G06T2207/10144 , G06T2207/20076 , G06T2207/20201 , H04N5/23267 , H04N5/35554
Abstract: A method for determining a deblurred image, the method implemented at least in part by a data processing system and comprising: receiving a sharp image of a scene captured with a short exposure time; receiving a blurred image of the scene captured with a longer exposure time than the sharp image, wherein the blurred image has a higher level of motion blur and a lower level of image noise than the sharp image; determining a blur kernel responsive to the sharp image and the blurred image; determining one or more reference differential images responsive to the sharp image; determining a deblurred image responsive to the blurred image, the blur kernel and the one or more reference differential images; and storing the deblurred image in a processor-accessible memory system.
Abstract translation: 一种用于确定去模糊图像的方法,所述方法至少部分地由数据处理系统实现,并且包括:接收以短曝光时间捕获的场景的清晰图像; 接收以比所述锐利图像更长的曝光时间拍摄的场景的模糊图像,其中所述模糊图像具有比所述锐利图像更高水平的运动模糊和较低水平的图像噪声; 确定响应于清晰图像和模糊图像的模糊内核; 确定响应于所述清晰图像的一个或多个参考差分图像; 确定响应于所述模糊图像,所述模糊核和所述一个或多个参考差分图像的去模糊图像; 以及将所述去模糊图像存储在处理器可访问存储器系统中。
-
公开(公告)号:US08379120B2
公开(公告)日:2013-02-19
申请号:US12612135
申请日:2009-11-04
Applicant: Sen Wang , Tingbo Hou , Rodney L. Miller
Inventor: Sen Wang , Tingbo Hou , Rodney L. Miller
CPC classification number: H04N5/23248 , G06T5/003 , G06T5/50 , G06T2207/20201 , H04N5/23277
Abstract: A method for determining a deblurred image comprising: receiving a blurred image of a scene; receiving a blur kernel; initializing a candidate deblurred image; determining a plurality of differential images representing differences between neighboring pixels in the candidate deblurred image; determining a combined differential image by combining the differential images; repeatedly updating the candidate deblurred image responsive to the blurred image, the blur kernel, the candidate deblurred image and the combined differential image until a convergence criterion is satisfied; and storing the final candidate deblurred image in a processor-accessible memory system.
Abstract translation: 一种用于确定去模糊图像的方法,包括:接收场景的模糊图像; 接收模糊内核; 初始化候选的未模糊图像; 确定表示候选去模糊图像中的相邻像素之间的差的多个差分图像; 通过组合差分图像来确定组合差分图像; 响应于模糊图像,模糊核心,候选去模糊图像和组合差分图像反复更新候选去模糊图像,直到满足收敛标准; 以及将最终的候选去模糊图像存储在处理器可访问的存储器系统中。
-
5.
公开(公告)号:US20110090378A1
公开(公告)日:2011-04-21
申请号:US12580591
申请日:2009-10-16
Applicant: Sen Wang , Tingbo Hou , Rodney L. Miller
Inventor: Sen Wang , Tingbo Hou , Rodney L. Miller
CPC classification number: H04N5/232 , G06T5/003 , G06T5/20 , G06T5/50 , G06T2207/10024 , G06T2207/10144 , H04N5/208 , H04N5/2355 , H04N9/045
Abstract: A method for determining a deblurred image from images captured using an image sensor comprising a two-dimensional array of light-sensitive pixels including panchromatic pixels and color pixels, the method comprising: receiving image sensor data from the image sensor for a sharp image of a scene captured with a short exposure time; receiving image sensor data from the image sensor for a blurred image of the scene captured with a longer exposure time than the sharp image; determining an interpolated sharp grayscale image from the sharp image; determining an interpolated blurred color image from the blurred image; determining an interpolated blurred grayscale image from the blurred image; determining a blur kernel responsive to the sharp grayscale image and the blurred grayscale image; determining a deblurred image responsive to the blurred color image and the blur kernel; and storing the deblurred image in a processor-accessible memory system.
Abstract translation: 一种用于使用包括包括全色像素和彩色像素的感光像素的二维阵列的图像传感器捕获的图像来确定去模糊图像的方法,所述方法包括:从图像传感器接收图像传感器数据,以获得 拍摄时间短的场景; 从图像传感器接收图像传感器数据,用于以比锐利图像更长的曝光时间拍摄的场景的模糊图像; 从锐利图像确定内插的锐度灰度图像; 从模糊图像确定内插的模糊彩色图像; 从所述模糊图像确定插值的模糊灰度图像; 确定响应于锐利灰度图像和模糊灰度图像的模糊内核; 确定响应于模糊的彩色图像和模糊核的去模糊图像; 以及将所述去模糊图像存储在处理器可访问存储器系统中。
-
-
-
-