-
公开(公告)号：US12118754B2
公开(公告)日：2024-10-15
申请号：US18494099
申请日：2023-10-25
发明人： Hau Hwang , Tushar Sinha Pankaj , Vishal Gupta , Jisoo Lee
IPC分类号： G06T7/90 , G06N3/04 , G06N20/00 , G06T3/06 , G06T3/4015
CPC分类号： G06T7/90 , G06N3/04 , G06N20/00 , G06T3/06 , G06T3/4015 , G06T2207/20084
摘要： Techniques are provided for using one or more machine learning systems to process input data including image data. The input data including the image data can be obtained, and at least one machine learning system can be applied to at least a portion of the image data to determine at least one color component value for one or more pixels of at least the portion of the image data. Based on application of the at least one machine learning system to at least the portion of the image data, output image data for a frame of output image data can be generated. The output image data includes at least one color component value for one or more pixels of the frame of output image data. Application of the at least one machine learning system causes the output image data to have a reduced dimensionality relative to the input data.
-
公开(公告)号：US11836951B2
公开(公告)日：2023-12-05
申请号：US17665281
申请日：2022-02-04
发明人： Hau Hwang , Tushar Sinha Pankaj , Vishal Gupta , Jisoo Lee
CPC分类号： G06T7/90 , G06N3/04 , G06N20/00 , G06T3/0031 , G06T3/4015 , G06T2207/20084
摘要： Techniques are provided for using one or more machine learning systems to process input data including image data. The input data including the image data can be obtained, and at least one machine learning system can be applied to at least a portion of the image data to determine at least one color component value for one or more pixels of at least the portion of the image data. Based on application of the at least one machine learning system to at least the portion of the image data, output image data for a frame of output image data can be generated. The output image data includes at least one color component value for one or more pixels of the frame of output image data. Application of the at least one machine learning system causes the output image data to have a reduced dimensionality relative to the input data.
-
公开(公告)号：US10375293B2
公开(公告)日：2019-08-06
申请号：US15692350
申请日：2017-08-31
发明人： Jisoo Lee
摘要： A method provides phase disparity data. First phase disparity data for a first image frame of a first scene is computed using a phase disparity engine of an image capture device. The method determines whether the image capture device is receiving light from a second scene that is different from the first scene and corresponds to a second image frame. The phase disparity engine discontinues computing of phase disparity data, in response to a determination that the second scene is not different from the first scene. The first phase disparity data are output in connection with the second image frame, in response to determining that the second scene is not different from the first scene.
-
公开(公告)号：US20190075233A1
公开(公告)日：2019-03-07
申请号：US15693855
申请日：2017-09-01
发明人： Micha Galor Gluskin , Prajit Kulkarni , Jisoo Lee
CPC分类号： H04N5/23212 , H01L27/14621 , H01L27/14623 , H01L27/14627 , H04N5/2254 , H04N5/232122 , H04N5/3696 , H04N5/36961 , H04N9/04557
摘要： Methods, systems, and apparatuses are provided to perform phase-detection autofocus control. By way of example, the methods can receive luminance values measured by a plurality of sensing elements in a sensor array, and the sensing elements can include imaging pixels and phase-detection pixels. The methods can compare luminance values measured by at least one of the phase-detection pixels to luminance values associated with a subset of the imaging pixels including two or more imaging pixels. The comparison can be performed at extended horizontal density or full horizontal density along a first sensor-array row that includes the at least one phase-detection pixel and the two or more imaging pixels. The methods can also perform a phase-detection autofocus operation based on an outcome of the comparison.
-
公开(公告)号：US20190068868A1
公开(公告)日：2019-02-28
申请号：US15692350
申请日：2017-08-31
发明人： Jisoo Lee
CPC分类号： H04N5/23212 , H04N5/144 , H04N5/232122 , H04N5/23241 , H04N5/232411 , H04N5/23245 , H04N5/23258 , H04N5/23261 , H04N5/36961 , H04N9/045
摘要： A method provides phase disparity data. First phase disparity data for a first image frame of a first scene is computed using a phase disparity engine of an image capture device. The method determines whether the image capture device is receiving light from a second scene that is different from the first scene and corresponds to a second image frame. The phase disparity engine discontinues computing of phase disparity data, in response to a determination that the second scene is not different from the first scene. The first phase disparity data are output in connection with the second image frame, in response to determining that the second scene is not different from the first scene.
-
公开(公告)号：US09910247B2
公开(公告)日：2018-03-06
申请号：US15002731
申请日：2016-01-21
发明人： Jisoo Lee , Leung Chun Chan
CPC分类号： G02B7/365 , H04N5/23212 , H04N5/3696
摘要： Methods and apparatuses for focus hunting prevention for phase detection auto focus (AF) are disclosed. In one aspect, the method is operable by an imaging device, for preventing focus hunting during a phase detection AF process. The method may include capturing an image of a scene and generating a phase difference value and a confidence level for the phase difference value based on the image. The method may also include calculating a focus hunting metric based at least in part on the phase difference value and the confidence level. The method may further include preventing focus hunting via at least one of preventing the start of the focus search and terminating the focus search, in response to the focus hunting metric meeting or exceeding a defined threshold value.
-
公开(公告)号：US20170090149A1
公开(公告)日：2017-03-30
申请号：US14865629
申请日：2015-09-25
CPC分类号： G02B7/285 , G02B7/34 , G02B7/365 , H01L27/14621 , H01L27/14627 , H04N5/23212 , H04N5/3696 , H04N9/045
摘要： Certain aspects relate to systems and techniques for using imaging pixels (that is, non-phase detection pixels) in addition to phase detection pixels for calculating autofocus information. Imaging pixel values can be used to interpolate a value at a phase detection pixel location. The interpolated value and a value received from the phase difference detection pixel can be used to obtain a virtual phase detection pixel value. The interpolated value, value received from the phase difference detection pixel, and the virtual phase detection pixel value can be used to obtain a phase difference detection signal indicating a shift direction (defocus direction) and a shift amount (defocus amount) of image focus.
-
公开(公告)号：US09420164B1
公开(公告)日：2016-08-16
申请号：US14865503
申请日：2015-09-25
IPC分类号： H04N5/232
CPC分类号： H04N5/23212 , G02B7/09 , G02B7/28 , G02B7/34 , G06T7/0002 , H01L27/14621 , H01L27/14627 , H01L27/14645 , H04N5/2254 , H04N5/3696 , H04N5/378
摘要： Certain aspects relate to systems and techniques for using imaging pixels (that is, non-phase detection pixels) for performing noise reduction on phase detection autofocus. Advantageously, this can provide for more accurate phase detection autofocus and also to optimized processor usage for performing phase detection. The phase difference detection pixels are provided to obtain a phase difference detection signal indicating a shift direction (defocus direction) and a shift amount (defocus amount) of image focus, and analysis of imaging pixel values can be used to estimate a level of focus of an in-focus region of interest and to limit the identified phase difference accordingly.
摘要翻译： 某些方面涉及用于在相位检测自动对焦上执行降噪的成像像素（即，非相位检测像素）的系统和技术。 有利的是，这可以提供更精确的相位检测自动对焦以及用于执行相位检测的优化的处理器使用。 提供相位差检测像素以获得指示图像焦点的偏移方向（散焦方向）和偏移量（散焦量）的相位差检测信号，并且可以使用成像像素值的分析来估计像素值的焦点水平 一个关注焦点的区域，并相应地限制所识别的相位差。
-
公开(公告)号：US11263782B2
公开(公告)日：2022-03-01
申请号：US16814783
申请日：2020-03-10
发明人： Hau Hwang , Tushar Sinha Pankaj , Vishal Gupta , Jisoo Lee
摘要： Techniques are provided for using one or more machine learning systems to process input data including image data. The input data including the image data can be obtained, and at least one machine learning system can be applied to at least a portion of the image data to determine at least one color component value for one or more pixels of at least the portion of the image data. Based on application of the at least one machine learning system to at least the portion of the image data, output image data for a frame of output image data can be generated. The output image data includes at least one color component value for one or more pixels of the frame of output image data. Application of the at least one machine learning system causes the output image data to have a reduced dimensionality relative to the input data.
-
公开(公告)号：US10904637B2
公开(公告)日：2021-01-26
申请号：US16222885
申请日：2018-12-17
IPC分类号： H04N7/173 , H04N21/6547 , G06N3/04 , G06N3/08 , H04N21/235 , H04N21/443 , H04N21/84
摘要： Techniques and systems are provided for providing a rendering engine model for raw media data. In some examples, a system obtains media data captured by a data capturing device and embeds, in a media item containing the media data, a rendering engine model including a description of a neural network configured to process the media data and generate a particular media data output, the description defining a neural network architecture for the neural network. The system then outputs the media item with the rendering engine model embedded in the media item, the rendering engine model indicating how to execute the neural network to process the media data in the media item and generate the particular media data output based on the description of the neural network.
-
-
-
-
-
-
-
-
-
搜索结果
29 条记录 (耗时 0.026 秒)
