METHOD AND APPARATUS FOR IMAGE PROCESSING
    1.
    发明申请
    METHOD AND APPARATUS FOR IMAGE PROCESSING 有权
    图像处理方法与装置

    公开(公告)号:US20150125093A1

    公开(公告)日:2015-05-07

    申请号:US14520440

    申请日:2014-10-22

    Abstract: A method and apparatus for image processing is provided, in which the method for image processing includes generating a base image based on multi-view color images and depth images corresponding to the multi-view color images, and generating a light field (LF) image, for example, an output image, based on the base image, that is, an image including occlusion regions of at least one LF image to be generated based on color images and depth images.

    Abstract translation: 提供了一种用于图像处理的方法和装置,其中图像处理方法包括基于多视角彩色图像和对应于多视角彩色图像的深度图像生成基本图像,并且生成光场(LF)图像 例如,基于基本图像的输出图像,即,包括基于彩色图像和深度图像而生成的至少一个LF图像的遮挡区域的图像。

    IMAGE PROCESSING METHOD AND APPARATUS FOR GENERATING DISPARITY VALUE
    3.
    发明申请
    IMAGE PROCESSING METHOD AND APPARATUS FOR GENERATING DISPARITY VALUE 有权
    图像处理方法和产生差异价值的装置

    公开(公告)号:US20130182945A1

    公开(公告)日:2013-07-18

    申请号:US13744916

    申请日:2013-01-18

    Abstract: A method and apparatus for processing an image is provided. The image processing apparatus may adjust or generate a disparity of a pixel, by assigning similar disparities to two pixels that are adjacent to each other and have similar pixels. The image processing apparatus may generate a final disparity map that may minimize energy, based on an image and an initial disparity map, under a predetermined constraint. A soft constraint or a hard constraint may be used as the constraint.

    Abstract translation: 提供了一种用于处理图像的方法和装置。 图像处理装置可以通过对彼此相邻并且具有相似像素的两个像素分配类似的差异来调整或生成像素的视差。 图像处理装置可以在预定约束下生成可基于图像和初始视差图来最小化能量的最终视差图。 可以使用软约束或硬约束作为约束。

    APPARATUS AND METHOD FOR RENDERING IMAGE
    5.
    发明申请
    APPARATUS AND METHOD FOR RENDERING IMAGE 审中-公开
    用于渲染图像的装置和方法

    公开(公告)号:US20160037153A1

    公开(公告)日:2016-02-04

    申请号:US14591184

    申请日:2015-01-07

    Abstract: An image rendering apparatus and method for rendering a stereoscopic image are provided. The image rendering apparatus may estimate a disparity of an image pixel included in an input image. Based on the disparity, a viewpoint direction of the image pixel may be determined by the image rendering apparatus. The image rendering apparatus may render a stereoscopic image by assigning a pixel value of the image pixel to a display pixel having a viewpoint direction corresponding to the viewpoint direction of the image pixel, instead of generating a multiview image.

    Abstract translation: 提供了一种用于渲染立体图像的图像渲染装置和方法。 图像再现装置可以估计包括在输入图像中的图像像素的视差。 基于视差,图像像素的视点方向可以由图像绘制装置确定。 图像渲染装置可以通过将图像像素的像素值分配给具有与图像像素的视点方向对应的视点方向的显示像素来呈现立体图像,而不是生成多视角图像。

    APPARATUS AND METHOD FOR ESTIMATING DISPARITY USING VISIBILITY ENERGY MODEL
    6.
    发明申请
    APPARATUS AND METHOD FOR ESTIMATING DISPARITY USING VISIBILITY ENERGY MODEL 有权
    使用可见性能量模型估计差异的装置和方法

    公开(公告)号:US20130223725A1

    公开(公告)日:2013-08-29

    申请号:US13771951

    申请日:2013-02-20

    CPC classification number: G06T7/0075 G06T7/593 G06T2207/10012

    Abstract: An apparatus and method for estimating disparity based on a visibility energy model includes an energy calculator to calculate energy related to stereo matching of each of a left image and a right image which constitute a stereo image, a map generator to generate a visibility map for determining an error in disparity between the left image and the right image using the energy, an energy recalculator to recalculate energy with respect to a region including a visibility error generated due to the error in disparity in the visibility map, and a disparity determiner to determine disparity from the stereo image using recalculated energy of each of the left image and the right image.

    Abstract translation: 一种用于基于能见度能量模型估计视差的装置和方法包括:能量计算器,用于计算与构成立体图像的左图像和右图像中的每一个的立体匹配相关的能量;地图生成器,用于生成用于确定 使用能量的左图像和右图像之间的差异误差,能量重新计算器相对于包括由于可见度图中的差异的误差而产生的可见性误差的区域重新计算能量,以及用于确定视差的视差确定器 从使用左图像和右图像中的每一个的重新计算的能量的立体图像。

    DISPLAY APPARATUS AND METHOD OF DESIGNING THE DISPLAY APPARATUS

    公开(公告)号:US20180095273A1

    公开(公告)日:2018-04-05

    申请号:US15463469

    申请日:2017-03-20

    CPC classification number: G02B27/0012 G02B27/2214

    Abstract: A display apparatus and a method of designing the display apparatus are provided. The display apparatus may include a display panel including a plurality of pixels to which a plurality of pieces of output information for outputting a three-dimensional image is allocated according to a sequence, and a grating layer including a plurality of grating elements configured to transfer, to the plurality of pixels, directional light according to the sequence, wherein the sequence is determined so that a distance between pieces of output information allocated to neighboring pixels among the plurality of pixels corresponds to a relatively prime number of a number of the plurality of pieces of output information allocated to the plurality of pixels.

    METHOD AND APPARATUS FOR GENERATING IMAGES
    10.
    发明申请
    METHOD AND APPARATUS FOR GENERATING IMAGES 有权
    用于生成图像的方法和装置

    公开(公告)号:US20170069128A1

    公开(公告)日:2017-03-09

    申请号:US15252863

    申请日:2016-08-31

    Abstract: A panel image that may be displayed in a display apparatus to display a 3D image that includes reduced differences with a source image may be generated based on generating a predicted 3D image based on a panel image, comparing the predicted 3D image to the source image, and adjusting the panel image to reduce differences between the predicted 3D image and the source image. Such a process may be performed iteratively. The predicted 3D image may be generated based on applying a convolution kernel to the panel image in a convolution operation. The convolution kernel may be based on a first function and a second function. The first function may be associated with a brightness distribution of one or more visual fields of the panel image. The second function may be associated with a Gaussian distribution of brightness of a panel image pixel.

    Abstract translation: 可以基于基于面板图像生成预测的3D图像,将预测的3D图像与源图像进行比较来生成可以在显示装置中显示以显示包含与源图像的差异的3D图像的面板图像, 并调整面板图像以减少预测3D图像和源图像之间的差异。 可以迭代地执行这样的处理。 可以基于在卷积运算中将卷积核应用于面板图像来生成预测3D图像。 卷积核可以基于第一函数和第二函数。 第一功能可以与面板图像的一个或多个视野的亮度分布相关联。 第二功能可以与面板图像像素的亮度的高斯分布相关联。

Patent Agency Ranking