Independent resizing of multiple image regions
    11.
    发明授权
    Independent resizing of multiple image regions 有权
    独立调整多个图像区域的大小

    公开(公告)号:US08160398B1

    公开(公告)日:2012-04-17

    申请号:US12183986

    申请日:2008-07-31

    IPC分类号: G06K9/32 G06K15/02 G09G5/00

    CPC分类号: G06T3/0012 H04N1/3875

    摘要: A system and method for expansion and reduction of images may apply resizing techniques independently to different regions of an input image to produce a resized version of the image having a specified target size and/or ratio. A content-aware resizing technique may be applied to some regions of the image. Each region may be reduced or expanded by the same amount based on local content, or different regions may be resized by different amounts to meet a resizing target for the input image. The same resizing technique may be applied to each region, or different resizing techniques may be applied to different regions. A given region or unselected portion of the image may not be resized at all. The techniques may be implemented by program instructions of an image editing application, and the definition of the regions and/or the selection of locally applied techniques may be configurable by a user.

    摘要翻译: 用于扩展和缩小图像的系统和方法可以独立地对输入图像的不同区域进行调整大小的技术以产生具有指定的目标尺寸和/或比率的图像的调整大小的版本。 可以将内容感知调整大小技术应用于图像的某些区域。 每个区域可以基于本地内容减少或扩展相同的量,或者可以通过不同的量来调整不同的区域以满足输入图像的调整大小目标。 可以将相同的调整尺寸技术应用于每个区域,或者可以将不同的调整尺寸技术应用于不同的区域。 图像的给定区域或未选择的部分根本不能调整大小。 这些技术可以通过图像编辑应用的程序指令来实现,并且区域的定义和/或本地应用的技术的选择可以由用户来配置。

    Denoising and artifact removal in image upscaling
    12.
    发明授权
    Denoising and artifact removal in image upscaling 有权
    图像放大中去噪和人工制品去除

    公开(公告)号:US08731337B2

    公开(公告)日:2014-05-20

    申请号:US13565379

    申请日:2012-08-02

    IPC分类号: G06K9/32 G06K9/00

    CPC分类号: G06T3/4053

    摘要: Methods and systems for denoising and artifact removal in image upscaling are disclosed. In one embodiment, a low frequency band image intermediate is obtained from an input image. An upsampled image intermediate is obtained from the input image by upsampling. A result image is estimated, based at least in part on the upsampled image intermediate, the low frequency band image intermediate, and the input image. The input image is of a smaller scale than the result image. The estimating the result image further includes eliminating from the result image noise that is present in the input image.

    摘要翻译: 公开了在图像升高中去除和去除伪影的方法和系统。 在一个实施例中,从输入图像获得低频带图像中间体。 通过上采样从输入图像获得上采样图像中间值。 至少部分地基于上采样图像中间,低频带图像中间和输入图像来估计结果图像。 输入图像的尺寸小于结果图像。 估计结果图像还包括消除输入图像中存在的结果图像噪声。

    Motion deblurring using image upsampling
    13.
    发明授权
    Motion deblurring using image upsampling 有权
    运动去模糊使用图像上采样

    公开(公告)号:US09042672B2

    公开(公告)日:2015-05-26

    申请号:US13480119

    申请日:2012-05-24

    IPC分类号: G06K9/40 G06T5/00

    CPC分类号: G06T5/003

    摘要: Various embodiments of methods and apparatus for motion deblurring are disclosed. In one embodiment, an estimate of a latent image of a blurred image at a current scale from an estimate of a latent image at a previous coarse scale is generated using an upsampling super-resolution function, and a blur kernel is estimated based on the estimate of the latent image and the blurred image; and are repeated from a course to fine scale. A final image estimate is generated. The generating the final image estimate includes performing a deconvolution of the latent image using the blur kernel and the blurred image.

    摘要翻译: 公开了用于运动去模糊的方法和装置的各种实施例。 在一个实施例中,使用上采样超分辨率函数,从先前粗略尺度的潜像估计值来估计当前尺度下的模糊图像的潜像,并且基于估计来估计模糊核 的潜像和模糊图像; 并从课程重复到精细规模。 生成最终图像估计。 生成最终图像估计包括使用模糊核和模糊图像执行潜像的去卷积。

    Motion Deblurring Using Image Upsampling
    14.
    发明申请
    Motion Deblurring Using Image Upsampling 有权
    使用图像上采样的运动去皱

    公开(公告)号:US20130058588A1

    公开(公告)日:2013-03-07

    申请号:US13480119

    申请日:2012-05-24

    IPC分类号: G06K9/40

    CPC分类号: G06T5/003

    摘要: Various embodiments of methods and apparatus for motion deblurring are disclosed. In one embodiment, an estimate of a latent image of a blurred image at a current scale from an estimate of a latent image at a previous coarse scale is generated using an upsampling super-resolution function, and a blur kernel is estimated based on the estimate of the latent image and the blurred image; and are repeated from a course to fine scale. A final image estimate is generated. The generating the final image estimate includes performing a deconvolution of the latent image using the blur kernel and the blurred image.

    摘要翻译: 公开了用于运动去模糊的方法和装置的各种实施例。 在一个实施例中,使用上采样超分辨率函数,从先前粗略尺度的潜像估计值来估计当前尺度下的模糊图像的潜像,并且基于估计来估计模糊核 的潜像和模糊图像; 并从课程重复到精细规模。 生成最终图像估计。 生成最终图像估计包括使用模糊核和模糊图像执行潜像的去卷积。

    Universal Front End for Masks, Selections, and Paths
    15.
    发明申请
    Universal Front End for Masks, Selections, and Paths 有权
    通用前端面具,选择和路径

    公开(公告)号:US20080144970A1

    公开(公告)日:2008-06-19

    申请号:US11610285

    申请日:2006-12-13

    IPC分类号: G06K9/20

    摘要: A method, system, and computer-readable storage medium are disclosed for editing a digital image with automatic conversion of region modalities. Input comprising an instruction to perform an operation on a first portion of the digital image may be received. The first portion of the digital image may comprise data defined by a first region modality. The operation may be applicable to data defined by a second region modality. In response to receiving the input, the first portion of the digital image may be automatically converted from the first region modality to the second region modality. The operation may be automatically performed on the converted first portion of the digital image (i.e., as defined by the second region modality).

    摘要翻译: 公开了用于通过区域模态的自动转换来编辑数字图像的方法,系统和计算机可读存储介质。 可以接收包括对数字图像的第一部分执行操作的指令的输入。 数字图像的第一部分可以包括由第一区域模态定义的数据。 该操作可以适用于由第二区域模态定义的数据。 响应于接收到输入,数字图像的第一部分可以自动地从第一区域模式转换到第二区域模态。 可以对数字图像的转换的第一部分(即,由第二区域模态定义)自动执行操作。

    Motion Deblurring for Text Images
    16.
    发明申请
    Motion Deblurring for Text Images 有权
    文本图像的运动解像

    公开(公告)号:US20130058587A1

    公开(公告)日:2013-03-07

    申请号:US13475483

    申请日:2012-05-18

    IPC分类号: G06K9/40

    CPC分类号: G06T5/003

    摘要: Various embodiments of methods and apparatus for motion deblurring in text images are disclosed. In one embodiment, a threshold-based text prediction for a blurred image is generated. A point spread function for the blurred image is estimated. A result of the threshold-based text prediction function is deconvolved based on the point spread function. The generating, estimating, and deconvolving are iterated at a plurality of scales, and a final deconvolution of a result of the iteratively deconvolving is executed.

    摘要翻译: 公开了用于文本图像中的运动去模糊的方法和装置的各种实施例。 在一个实施例中,生成用于模糊图像的基于阈值的文本预测。 估计模糊图像的点扩散函数。 基于阈值的文本预测函数的结果基于点扩散函数被去卷积。 生成,估计和解卷积以多个尺度迭代,并且执行迭代去卷积的结果的最终去卷积。

    Robust Patch Regression based on In-Place Self-similarity for Image Upscaling
    17.
    发明申请
    Robust Patch Regression based on In-Place Self-similarity for Image Upscaling 有权
    基于图像升高的就地自相似性的鲁棒补丁回归

    公开(公告)号:US20130034299A1

    公开(公告)日:2013-02-07

    申请号:US13565411

    申请日:2012-08-02

    IPC分类号: G06K9/32

    CPC分类号: G06T3/4053

    摘要: Methods and systems for image upscaling are disclosed. In one embodiment, a low frequency band image intermediate is obtained from an input image. The input image is upsampled by a scale factor to obtain an upsampled image intermediate. A result image is estimated based at least in part on the upsampled image intermediate, the low frequency band image intermediate, and the input image, wherein the input image is of a smaller scale than the result image.

    摘要翻译: 公开了用于图像放大的方法和系统。 在一个实施例中,从输入图像获得低频带图像中间体。 输入图像由比例因子上采样,以获得上采样图像中间值。 至少部分地基于上采样图像中间,低频带图像中间和输入图像来估计结果图像,其中输入图像比结果图像小一些。

    Motion deblurring for text images
    18.
    发明授权
    Motion deblurring for text images 有权
    文本图像的运动去模糊

    公开(公告)号:US08705881B2

    公开(公告)日:2014-04-22

    申请号:US13475483

    申请日:2012-05-18

    IPC分类号: G06K9/40 G06K9/64

    CPC分类号: G06T5/003

    摘要: Various embodiments of methods and apparatus for motion deblurring in text images are disclosed. In one embodiment, a threshold-based text prediction for a blurred image is generated. A point spread function for the blurred image is estimated. A result of the threshold-based text prediction function is deconvolved based on the point spread function. The generating, estimating, and deconvolving are iterated at a plurality of scales, and a final deconvolution of a result of the iteratively deconvolving is executed.

    摘要翻译: 公开了用于文本图像中的运动去模糊的方法和装置的各种实施例。 在一个实施例中,生成用于模糊图像的基于阈值的文本预测。 估计模糊图像的点扩散函数。 基于阈值的文本预测函数的结果基于点扩散函数被去卷积。 生成,估计和解卷积以多个尺度迭代,并且执行迭代去卷积的结果的最终去卷积。

    Robust patch regression based on in-place self-similarity for image upscaling
    19.
    发明授权
    Robust patch regression based on in-place self-similarity for image upscaling 有权
    基于图像放大的就地自相似性的鲁棒贴片回归

    公开(公告)号:US08687923B2

    公开(公告)日:2014-04-01

    申请号:US13565411

    申请日:2012-08-02

    IPC分类号: G06K9/32 G06K9/00

    CPC分类号: G06T3/4053

    摘要: Methods and systems for image upscaling are disclosed. In one embodiment, a low frequency band image intermediate is obtained from an input image. The input image is upsampled by a scale factor to obtain an upsampled image intermediate. A result image is estimated based at least in part on the upsampled image intermediate, the low frequency band image intermediate, and the input image, wherein the input image is of a smaller scale than the result image.

    摘要翻译: 公开了用于图像放大的方法和系统。 在一个实施例中,从输入图像获得低频带图像中间体。 输入图像由比例因子上采样,以获得上采样图像中间值。 至少部分地基于上采样图像中间,低频带图像中间和输入图像来估计结果图像,其中输入图像比结果图像小一些。

    Regression-based learning model for image upscaling
    20.
    发明授权
    Regression-based learning model for image upscaling 有权
    基于回归的图像增大学习模型

    公开(公告)号:US08655109B2

    公开(公告)日:2014-02-18

    申请号:US13565334

    申请日:2012-08-02

    IPC分类号: G06K9/32 G06K9/00

    CPC分类号: G06T3/4053

    摘要: Methods and systems for a regression-based learning model in image upscaling are disclosed. In one embodiment, a set of image patch pairs for each of a set of images is generated. Each of the image patch pairs contains a natural image and a corresponding downscaled lower-resolution image. A regression model based at least in part on the set of image patch pairs is defined. The regression model represents a gradient of a function of the downscaled lower-resolution image. An image is upscaled based at least in part on the regression model.

    摘要翻译: 公开了一种基于回归的学习模型在图像放大中的方法和系统。 在一个实施例中,生成用于一组图像中的每一个的一组图像补丁对。 每个图像补丁对包含自然图像和对应的缩小的较低分辨率图像。 定义了至少部分基于图像补丁对集合的回归模型。 回归模型表示缩小的较低分辨率图像的函数的梯度。 至少部分基于回归模型,图像被放大。