利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

7 条记录 (耗时 0.022 秒)

    IMAGE INTERPOLATION METHOD AND DEVICE BASED ON AUTOREGRESSIVE MODEL
    1.
    发明申请
    IMAGE INTERPOLATION METHOD AND DEVICE BASED ON AUTOREGRESSIVE MODEL 有权
    基于自适应模型的图像插值方法和装置

    公开(公告)号：US20150262334A1

    公开(公告)日：2015-09-17

    申请号：US14434975

    申请日：2013-11-06

    申请人： PEKING UNIVERSITY ,  PEKING UNIVERSITY FOUNDER GROUP CO., LTD. ,  BEIJING FOUNDER ELECTRONICS CO., LTD.

    发明人： Mading Li ,  Jiaying Liu ,  Jie Ren ,  Zongming Guo

    IPC分类号： G06T3/40 ,  G06T5/50

    CPC分类号： G06T3/4007 ,  G06T5/50 ,  G06T2207/20224

    摘要： An image interpolation method and device based on an autoregressive model. The method first, interpolating a low-resolution image up to a target scale to obtain an interpolated image M; determining a local area W in the image M to be interpolated, establishing two autoregressive models for each pixel point in the local area W except for the edge pixel points, and determining an initial objective function F0 according to the autoregressive models; down sampling the local area W except for the edge pixel points to the same size as the low-resolution image to obtain a local area W′, subtracting a corresponding area in the low-resolution image from W′ one pixel value by one pixel value, and adding the result to the initial objective function F0 to obtain an objective function F; performing iteration on the objective function F to obtain a pixel point value of a center block of W.

    摘要翻译： 一种基于自回归模型的图像插值方法和装置。 该方法首先将低分辨率图像内插到目标尺度以获得内插图像M; 确定要内插的图像M中的局部区域W，为除了边缘像素点之外的局部区域W中的每个像素点建立两个自回归模型，以及根据自回归模型确定初始目标函数F0; 将边缘像素点除以与低分辨率图像相同的尺寸的局部区域W进行下采样以获得局部区域W'，从W'一个像素值减去一个像素值的低分辨率图像中的对应区域 并将结果加到初始目标函数F0以获得目标函数F; 对目标函数F执行迭代以获得W的中心块的像素点值。

    Image interpolation method and device based on autoregressive model
    4.
    发明授权
    Image interpolation method and device based on autoregressive model 有权

    公开(公告)号：US09672590B2

    公开(公告)日：2017-06-06

    申请号：US14434975

    申请日：2013-11-06

    申请人： Peking University ,  Peking University Founder Group Co., Ltd. ,  Beijing Founder Electronics Co., Ltd.

    发明人： Mading Li ,  Jiaying Liu ,  Jie Ren ,  Zongming Guo

    IPC分类号： G06T3/40 ,  G06T5/50

    CPC分类号： G06T3/4007 ,  G06T5/50 ,  G06T2207/20224

    摘要： An image interpolation method and device based on an autoregressive model. The method first, interpolating a low-resolution image up to a target scale to obtain an interpolated image M; determining a local area W in the image M to be interpolated, establishing two autoregressive models for each pixel point in the local area W except for the edge pixel points, and determining an initial objective function F0 according to the autoregressive models; down sampling the local area W except for the edge pixel points to the same size as the low-resolution image to obtain a local area W′, subtracting a corresponding area in the low-resolution image from W′ one pixel value by one pixel value, and adding the result to the initial objective function F0 to obtain an objective function F; performing iteration on the objective function F to obtain a pixel point value of a center block of W.

    Nonlocality based super resolution reconstruction method and device
    5.
    发明授权
    Nonlocality based super resolution reconstruction method and device 有权
    基于非局部性的超分辨率重构方法及装置

    公开(公告)号：US09111367B2

    公开(公告)日：2015-08-18

    申请号：US14129764

    申请日：2012-12-13

    申请人： Peking University ,  Peking University Founder Group Co., Ltd. ,  Beijing Founder Electronics Co., Ltd.

    发明人： Jiaying Liu ,  Yue Zhou ,  Jie Ren ,  Zongming Guo

    IPC分类号： G06K9/36 ,  G06T3/40 ,  H04N19/51 ,  H04N19/59

    CPC分类号： G06T3/4053 ,  H04N19/51 ,  H04N19/59

    摘要： The present invention relates to the field of digital image enhancement technologies, and more particularly to a non-locality-based super-resolution reconstruction method and device, so as to solve the problem of relatively low resolution of an image after non-locality-based super-resolution reconstruction in the prior art. The method in the embodiment of the present invention comprises: determining a position of a search window where a current macro-block is mapped in each of other image frames; determining a search window where the current pixel block is mapped in the each of the image frames, according to the position of the search window where the macro-block, where the pixel corresponding to the current pixel block is located, is mapped in the each of the image frames, and determining a similarity value of each determined pixel block in the determined search window relative to the current pixel block respectively; and determining an optimized central pixel value of each pixel block according to the determined similarity value. By use of the embodiments of the present invention, the resolution of an image subjected to non-locality-based super-resolution reconstruction is enhanced.

    摘要翻译： 本发明涉及数字图像增强技术的领域，更具体地涉及一种基于非局部性的超分辨率重建方法和装置，以解决非局部性之后图像分辨率相对较低的问题 现有技术中的超分辨率重构。 本发明实施例中的方法包括：确定当前宏块映射到其他图像帧的每一个中的搜索窗口的位置; 根据搜索窗口的位置来确定当前像素块被映射到每个图像帧中的搜索窗口，其中与当前像素块相对应的像素所在的宏块被映射到每个 并且确定所确定的搜索窗口中的每个确定的像素块相对于当前像素块的相似度值; 以及根据所确定的相似度值确定每个像素块的优化的中心像素值。 通过使用本发明的实施例，增强了经受基于非局部性的超分辨率重构的图像的分辨率。

    NONLOCALITY BASED SUPER RESOLUTION RECONSTRUCTION METHOD AND DEVICE
    6.
    发明申请
    NONLOCALITY BASED SUPER RESOLUTION RECONSTRUCTION METHOD AND DEVICE 有权
    非基于超分辨率重建方法和设备

    公开(公告)号：US20140133780A1

    公开(公告)日：2014-05-15

    申请号：US14129764

    申请日：2012-12-13

    申请人： Perking University ,  Beijing Founder Electronics Co., Ltd. ,  Perking University Founder Group Co., Ltd.

    发明人： Jiaying Liu ,  Yue Zhou ,  Jie Ren ,  Zongming Guo

    IPC分类号： G06T3/40

    CPC分类号： G06T3/4053 ,  H04N19/51 ,  H04N19/59

    摘要： The present invention relates to the field of digital image enhancement technologies, and more particularly to a non-locality-based super-resolution reconstruction method and device, so as to solve the problem of relatively low resolution of an image after non-locality-based super-resolution reconstruction in the prior art. The method in the embodiment of the present invention comprises: determining a position of a search window where a current macro-block is mapped in each of other image frames; determining a search window where the current pixel block is mapped in the each of the image frames, according to the position of the search window where the macro-block, where the pixel corresponding to the current pixel block is located, is mapped in the each of the image frames, and determining a similarity value of each determined pixel block in the determined search window relative to the current pixel block respectively; and determining an optimized central pixel value of each pixel block according to the determined similarity value. By use of the embodiments of the present invention, the resolution of an image subjected to non-locality-based super-resolution reconstruction is enhanced.

    摘要翻译： 本发明涉及数字图像增强技术的领域，更具体地涉及一种基于非局部性的超分辨率重建方法和装置，以解决非局部性之后图像分辨率相对较低的问题 现有技术中的超分辨率重构。 本发明实施例中的方法包括：确定当前宏块映射到其他图像帧的每一个中的搜索窗口的位置; 根据搜索窗口的位置来确定当前像素块被映射到每个图像帧中的搜索窗口，其中与当前像素块相对应的像素所在的宏块被映射到每个 并且确定所确定的搜索窗口中的每个确定的像素块相对于当前像素块的相似度值; 以及根据所确定的相似度值确定每个像素块的优化的中心像素值。 通过使用本发明的实施例，增强了经受基于非局部性的超分辨率重构的图像的分辨率。