Apparatus and method for generating extrapolated view based on image resizing
    1.
    发明授权
    Apparatus and method for generating extrapolated view based on image resizing 有权
    基于图像调整大小生成外推视图的装置和方法

    公开(公告)号:US08634675B2

    公开(公告)日:2014-01-21

    申请号:US13177945

    申请日:2011-07-07

    IPC分类号: G06K9/36

    CPC分类号: G06T15/205 H04N13/111

    摘要: A view extrapolation apparatus and a view extrapolation method to generate images at a plurality of virtual points using a relatively small number of input images are disclosed. The view extrapolation apparatus and the view extrapolation method output a view at a reference point, the view at the reference point being formed of frames according to time, generating the frames of the view at the reference point to generate a resized frame, and generating an extrapolated view at a virtual point using the resized frame.

    摘要翻译: 公开了使用相对较少数量的输入图像在多个虚拟点生成图像的视图外推装置和视图外插方法。 视图外推装置和视图外插方法在参考点处输出视图,参考点处的视图由根据时间的帧形成,在参考点处生成视图的帧以生成调整大小的帧,并且生成 使用调整大小的框架在虚拟点进行外推视图。

    Method and apparatus for processing multi-view image using hole rendering
    2.
    发明授权
    Method and apparatus for processing multi-view image using hole rendering 有权
    使用孔渲染处理多视图图像的方法和装置

    公开(公告)号:US08873834B2

    公开(公告)日:2014-10-28

    申请号:US13467640

    申请日:2012-05-09

    IPC分类号: G06T15/00 H04N13/00

    摘要: A method and apparatus for processing a multi-view image are provided. A priority may be assigned to each hole pixel in a hole region generated when an output view is generated. The priority of each hole pixel may be generated by combining a structure priority, a confidence priority, and a disparity priority. Hole rendering may be applied to a target patch including a hole pixel having a highest priority. The hole pixel may be restored by searching for a source patch most similar to a background of the target patch, and copying a pixel in the found source patch into a hole pixel of the target patch.

    摘要翻译: 提供了一种用于处理多视图图像的方法和装置。 可以在产生输出视图时产生的孔区域中的每个孔像素分配优先权。 可以通过组合结构优先级,置信优先级和视差优先级来生成每个空穴像素的优先级。 空穴描绘可以应用于包括具有最高优先级的孔像素的目标贴片。 可以通过搜索与目标补丁的背景最相似的源补丁,并将找到的源补丁中的像素复制到目标补丁的孔像素中来恢复孔像素。

    IMAGE PROCESSING METHOD AND APPARATUS
    4.
    发明申请
    IMAGE PROCESSING METHOD AND APPARATUS 审中-公开
    图像处理方法和装置

    公开(公告)号:US20120313932A1

    公开(公告)日:2012-12-13

    申请号:US13489772

    申请日:2012-06-06

    IPC分类号: G06T15/00

    CPC分类号: G06T15/205

    摘要: An image processing method and apparatus may generate a reference layer about a reference viewpoint. The reference layer may include information used to perform a hole recovery with respect to holes within output images. The information may be generated by warping the reference layer to a viewpoint of an output image.

    摘要翻译: 图像处理方法和装置可以生成关于参考视点的参考层。 参考层可以包括用于对输出图像内的孔执行孔恢复的信息。 可以通过使参考层翘曲到输出图像的视点来生成信息。

    System and method producing high definition video from low definition video
    5.
    发明授权
    System and method producing high definition video from low definition video 有权
    从低分辨率视频产生高分辨率视频的系统和方法

    公开(公告)号:US09179092B2

    公开(公告)日:2015-11-03

    申请号:US12923439

    申请日:2010-09-21

    IPC分类号: H04N7/01 G06T3/40

    摘要: Provided is system and a method of producing a high definition video from a low definition video. According to one or more embodiments, the method performs a trajectory estimation and a matching operation only with respect to a feature region pixel of a previous frame of the low definition video, which is different from all pixels of the previous frame, thereby reducing an amount of computation to improve efficiency of a memory, producing the high definition video in real time, and producing a more accurate high definition video with respect to a feature region.

    摘要翻译: 提供的是从低分辨率视频产生高分辨率视频的系统和方法。 根据一个或多个实施例,该方法仅针对低分辨率视频的前一帧的特征区域像素执行轨迹估计和匹配操作,其不同于前一帧的所有像素,从而减少了量 的计算以提高存储器的效率,实时产生高清晰度视频,并且相对于特征区域产生更准确的高清晰度视频。

    System and method producing high definition video from low definition video
    8.
    发明申请
    System and method producing high definition video from low definition video 有权
    从低分辨率视频产生高分辨率视频的系统和方法

    公开(公告)号:US20110075025A1

    公开(公告)日:2011-03-31

    申请号:US12923439

    申请日:2010-09-21

    IPC分类号: H04N7/01

    摘要: Provided is system and a method of producing a high definition video from a low definition video. According to one or more embodiments, the method performs a trajectory estimation and a matching operation only with respect to a feature region pixel of a previous frame of the low definition video, which is different from all pixels of the previous frame, thereby reducing an amount of computation to improve efficiency of a memory, producing the high definition video in real time, and producing a more accurate high definition video with respect to a feature region.

    摘要翻译: 提供的是从低分辨率视频产生高分辨率视频的系统和方法。 根据一个或多个实施例,该方法仅针对低分辨率视频的前一帧的特征区域像素执行轨迹估计和匹配操作,其不同于前一帧的所有像素,从而减少了量 的计算以提高存储器的效率,实时产生高清晰度视频,并且相对于特征区域产生更准确的高清晰度视频。

    METHOD AND APPARATUS GENERATING MULTI-VIEW IMAGES FOR THREE-DIMENSIONAL DISPLAY
    9.
    发明申请
    METHOD AND APPARATUS GENERATING MULTI-VIEW IMAGES FOR THREE-DIMENSIONAL DISPLAY 有权
    生成三维显示的多视图的方法和装置

    公开(公告)号:US20120169722A1

    公开(公告)日:2012-07-05

    申请号:US13326757

    申请日:2011-12-15

    IPC分类号: G06T15/00

    CPC分类号: H04N13/111 H04N2213/005

    摘要: A method and apparatus for generating multi-view images are provided. An error suspicious area may be detected from a reference view image. A foreground-first image may be generated by foreground-first warping including regarding the error suspicious area as a foreground, and a background-first image may be generated by background-first warping including regarding the error suspicious area as a background. The foreground-first image and the background-first image may be blended, and an output view image in a predetermined viewpoint may be generated.

    摘要翻译: 提供了一种用于产生多视图图像的方法和装置。 可以从参考视图图像检测到错误可疑区域。 前景第一图像可以通过前景第一翘曲生成,包括将错误可疑区域作为前景,并且背景优先图像可以通过包括关于错误可疑区域作为背景的背景优先生成。 可以混合前景第一图像和背景优先图像,并且可以生成预定视点中的输出视图图像。

    Apparatus and method for generating extrapolated view
    10.
    发明授权
    Apparatus and method for generating extrapolated view 有权
    用于产生外推视图的装置和方法

    公开(公告)号:US08803947B2

    公开(公告)日:2014-08-12

    申请号:US13154947

    申请日:2011-06-07

    IPC分类号: H04N13/00

    摘要: A view extrapolation apparatus and a view extrapolation method to generate images at a plurality of virtual points uses a relatively small number of input images. The view extrapolation apparatus and the view extrapolation method output a view at a reference point, the view at the reference point being formed of frames generated chronologically, integrate a plurality of successive frames of the view at the reference point to generate an integrated frame, and generate an extrapolated view at a virtual point using the integrated frame.

    摘要翻译: 视图外推装置和用于在多个虚拟点产生图像的视图外插方法使用相对较少数量的输入图像。 视图外推装置和视图外插方法在参考点处输出视图,参考点处的视图由按时间顺序生成的帧形成,在参考点处整合视图的多个连续帧以产生一个集成的帧,以及 使用集成框架在虚拟点生成外推视图。