Video processing method for 3D display based on multi-cue process
    2.
    发明申请
    Video processing method for 3D display based on multi-cue process 有权
    基于多线程过程的3D显示视频处理方法

    公开(公告)号:US20120007960A1

    公开(公告)日:2012-01-12

    申请号:US13067465

    申请日:2011-06-02

    IPC分类号: H04N13/04

    摘要: A video processing method for a three-dimensional (3D) display is based on a multi-cue process. The method may include acquiring a cut boundary of a shot by performing a shot boundary detection with respect to each frame of an input video, computing a texture saliency with respect to each pixel of the input video, computing a motion saliency with respect to each pixel of the input video, computing an object saliency with respect to each pixel of the input video based on the acquired cut boundary of the shot, acquiring a universal saliency with respect to each pixel of the input video by combining the texture saliency, the motion saliency, and the object saliency, and smoothening the universal saliency of each pixel using a space-time technology.

    摘要翻译: 用于三维(3D)显示的视频处理方法基于多提示过程。 该方法可以包括通过对输入视频的每个帧执行镜头边界检测来获取镜头的切割边界,计算相对于输入视频的每个像素的纹理显着性,计算相对于每个像素的运动显着性 基于拍摄的所获取的切割边界,针对输入视频的每个像素计算对象的显着性,通过组合纹理显着性,运动显着性来获取关于输入视频的每个像素的通用显着性 和物体的显着性,并利用时空技术平滑每个像素的普遍显着性。

    Video processing method for 3D display based on multi-cue process
    3.
    发明授权
    Video processing method for 3D display based on multi-cue process 有权
    基于多线程过程的3D显示视频处理方法

    公开(公告)号:US09148652B2

    公开(公告)日:2015-09-29

    申请号:US13067465

    申请日:2011-06-02

    摘要: A video processing method for a three-dimensional (3D) display is based on a multi-cue process. The method may include acquiring a cut boundary of a shot by performing a shot boundary detection with respect to each frame of an input video, computing a texture saliency with respect to each pixel of the input video, computing a motion saliency with respect to each pixel of the input video, computing an object saliency with respect to each pixel of the input video based on the acquired cut boundary of the shot, acquiring a universal saliency with respect to each pixel of the input video by combining the texture saliency, the motion saliency, and the object saliency, and smoothening the universal saliency of each pixel using a space-time technology.

    摘要翻译: 用于三维(3D)显示的视频处理方法基于多提示过程。 该方法可以包括通过对输入视频的每个帧执行镜头边界检测来获取镜头的切割边界,计算相对于输入视频的每个像素的纹理显着性,计算相对于每个像素的运动显着性 基于拍摄的所获取的切割边界,针对输入视频的每个像素计算对象的显着性,通过组合纹理显着性,运动显着性来获取关于输入视频的每个像素的通用显着性 和物体的显着性,并利用时空技术平滑每个像素的普遍显着性。

    3D IMAGE GENERATION APPARATUS AND METHOD
    5.
    发明申请
    3D IMAGE GENERATION APPARATUS AND METHOD 有权
    3D图像生成装置和方法

    公开(公告)号:US20100110070A1

    公开(公告)日:2010-05-06

    申请号:US12402732

    申请日:2009-03-12

    IPC分类号: G06T15/00

    摘要: A three-dimensional (3D) image generator and 3D image generation method scale a depth map or a two-dimensional (2D) image, perform a cross filtering to sharpen a blurred region on the depth map based on location information of the depth map and 2D image, and thus obtain a clearer depth map and provide a more graphical 3D image using the depth map.

    摘要翻译: 三维(3D)图像生成器和3D图像生成方法对深度图或二维(2D)图像进行缩放,基于深度图的位置信息进行交叉滤波以锐化深度图上的模糊区域,并且 2D图像,从而获得更清晰的深度图,并使用深度图提供更多图形的3D图像。

    3D image generation apparatus and method
    8.
    发明授权
    3D image generation apparatus and method 有权
    3D图像生成装置和方法

    公开(公告)号:US08253733B2

    公开(公告)日:2012-08-28

    申请号:US12402732

    申请日:2009-03-12

    IPC分类号: G06T15/00 G06K9/32 G06F17/17

    摘要: A three-dimensional (3D) image generator and 3D image generation method scale a depth map or a two-dimensional (2D) image, perform a cross filtering to sharpen a blurred region on the depth map based on location information of the depth map and 2D image, and thus obtain a clearer depth map and provide a more graphical 3D image using the depth map.

    摘要翻译: 三维(3D)图像生成器和3D图像生成方法对深度图或二维(2D)图像进行缩放,基于深度图的位置信息进行交叉滤波以锐化深度图上的模糊区域,并且 2D图像,从而获得更清晰的深度图,并使用深度图提供更多图形的3D图像。

    Three-dimensional image generation apparatus and method using region extension of object in depth map
    9.
    发明申请
    Three-dimensional image generation apparatus and method using region extension of object in depth map 审中-公开
    三维图像生成装置和方法使用区域扩展对象的深度图

    公开(公告)号:US20100316284A1

    公开(公告)日:2010-12-16

    申请号:US12656840

    申请日:2010-02-17

    IPC分类号: G06K9/00

    摘要: A three-dimensional (3D) image generation apparatus and method using a region extension of an object in a depth map is provided. The 3D image generation apparatus may include a discontinuity preservation smoothing filtering unit to apply a discontinuity preservation smoothing filter preserving discontinuity of a boundary or a shape of a depth image, a boundary preservation filtering unit to apply a max filter to a depth image for increasing a depth value of an object, and a rendering unit to render a two-dimensional (2D) color image and the filtered depth image and to generate a 3D image.

    摘要翻译: 提供了一种在深度图中使用对象的区域扩展的三维(3D)图像生成装置和方法。 3D图像生成装置可以包括不连续保存平滑滤波单元,用于应用保持边界的不连续性或深度图像的形状的不连续性保存平滑滤波器,边界保存滤波单元,对深度图像应用最大滤波器以增加 物体的深度值,以及呈现二维(2D)彩色图像和滤波后的深度图像并生成3D图像的渲染单元。