Method And Apparatus For Converting A Two-Dimensional Image Into A Three-Dimensional Stereoscopic Image
    1.
    发明申请
    Method And Apparatus For Converting A Two-Dimensional Image Into A Three-Dimensional Stereoscopic Image 有权
    用于将二维图像转换为三维立体图像的方法和装置

    公开(公告)号:US20120086775A1

    公开(公告)日:2012-04-12

    申请号:US12900053

    申请日:2010-10-07

    IPC分类号: H04N13/02 G06K9/00

    摘要: A method and apparatus for converting a two-dimensional image into a stereoscopic three-dimensional image. In one embodiment, a computer implemented method of converting a two-dimensional image into a stereoscopic three-dimensional image including for each pixel within a right eye image, identifying at least one corresponding pixel from a left eye image and determining a depth and an intensity value for the each pixel within the right eye image using the at least one corresponding pixel, wherein the depth value is stored in a right eye depth map and the intensity value is stored in the right eye image and inpainting at least one occluded region within the right eye image using the right eye depth map.

    摘要翻译: 一种用于将二维图像转换成立体三维图像的方法和装置。 在一个实施例中,一种计算机实现的方法,其将二维图像转换为包括右眼图像内的每个像素的立体三维图像,从左眼图像识别至少一个相应像素,并确定深度和强度 使用所述至少一个对应像素在所述右眼图像内的每个像素的值,其中所述深度值存储在右眼深度图中,并且所述强度值被存储在所述右眼图像中并且在所述至少一个遮挡区域内修复 右眼图像使用右眼深度图。

    Method and apparatus for converting a two-dimensional image into a three-dimensional stereoscopic image
    2.
    发明授权
    Method and apparatus for converting a two-dimensional image into a three-dimensional stereoscopic image 有权
    将二维图像转换为三维立体图像的方法和装置

    公开(公告)号:US08902283B2

    公开(公告)日:2014-12-02

    申请号:US12900053

    申请日:2010-10-07

    IPC分类号: H04N13/00 H04N13/02 G06T15/40

    摘要: The present invention is directed to a method and apparatus for converting a two-dimensional image into a stereoscopic three-dimensional image. In one embodiment, a method of converting a two-dimensional image into a stereoscopic three-dimensional image comprises identifying at least one corresponding pixel from a left eye image and determining a depth and an intensity value for the each pixel within a right eye image using the at least one corresponding pixel. The depth value is stored in a right eye depth map and the intensity value is stored in the right eye image. The method further comprises inpainting at least one occluded region within the right eye image using the right eye depth map.

    摘要翻译: 本发明涉及将二维图像转换为立体三维图像的方法和装置。 在一个实施例中,将二维图像转换为立体三维图像的方法包括从左眼图像识别至少一个对应像素,并且使用以下方法确定右眼图像内的每个像素的深度和强度值 所述至少一个对应的像素。 深度值存储在右眼深度图中,强度值存储在右眼图像中。 该方法还包括使用右眼深度图来修饰右眼图像内的至少一个闭塞区域。

    Method and apparatus for multiview image generation using depth map information
    3.
    发明授权
    Method and apparatus for multiview image generation using depth map information 失效
    使用深度图信息的多视图图像生成方法和装置

    公开(公告)号:US08773427B2

    公开(公告)日:2014-07-08

    申请号:US12976944

    申请日:2010-12-22

    IPC分类号: G06T15/00 G06T7/00

    摘要: A method and apparatus for multiview image generation using depth map information is described. In one embodiment, a computer-implemented method comprises converting a input image and an input depth map into a projected image and a projected depth map using values from physical pixel locations that map to projected pixel locations, wherein the projected image and the projected depth map are associated with a particular view of the input image, inpainting the projected image and the projected depth map and producing an output image in a direction of the particular view using the inpainted projected image and the inpainted projected depth map.

    摘要翻译: 描述了使用深度图信息进行多视图图像生成的方法和装置。 在一个实施例中,计算机实现的方法包括使用映射到投影像素位置的物理像素位置的值将输入图像和输入深度图转换为投影图像和投影深度图,其中投影图像和投影深度图 与输入图像的特定视图相关联,对投影图像和投影深度图进行修复,并且使用未修补的投影图像和未修补的投影深度图在特定视图的方向上产生输出图像。

    Method for device spectral sensitivity reconstruction
    4.
    发明申请
    Method for device spectral sensitivity reconstruction 有权
    器件光谱灵敏度重建方法

    公开(公告)号:US20070229666A1

    公开(公告)日:2007-10-04

    申请号:US11398196

    申请日:2006-04-04

    IPC分类号: H04N17/00

    CPC分类号: H04N17/002 H04N9/045

    摘要: A method and system are provided for approximating spectral sensitivities of a particular image sensor, the image sensor having a color filter array positioned over the image sensor. In one example of the method, the method involves measuring spectral sensitivities of a set of image sensors each having a color filter array positioned over the image sensor, calculating mean spectral sensitivities of the set of image sensors for each color within the color filter array, measuring outputs of a particular image sensor when capturing a picture of a plurality of color patches under a first illuminant and calculating spectral sensitivities of the particular image sensor using the mean spectral sensitivities and the output of the particular image sensor. In some embodiments, the method further comprises utilizing the calculated spectral sensitivities to determine outputs of the particular image sensor under a second illuminant. In some embodiments, the method further comprises utilizing the calculated spectral sensitivities to calibrate a camera including the image sensor.

    摘要翻译: 提供了用于近似特定图像传感器的光谱灵敏度的方法和系统,该图像传感器具有位于图像传感器上方的滤色器阵列。 在该方法的一个示例中,该方法涉及测量一组图像传感器的光谱灵敏度,每个图像传感器具有位于图像传感器上方的滤色器阵列,计算滤色器阵列内每种颜色的图像传感器组的平均光谱灵敏度, 测量特定图像传感器的输出,当在第一光源下拍摄多个色块的图像时,使用平均光谱灵敏度和特定图像传感器的输出来计算特定图像传感器的光谱灵敏度。 在一些实施例中,该方法还包括利用所计算的光谱灵敏度来确定第二光源下的特定图像传感器的输出。 在一些实施例中,该方法还包括利用所计算的光谱灵敏度来校准包括图像传感器的照相机。

    Error analysis for image interpolation and demosaicing using lattice theory
    5.
    发明申请
    Error analysis for image interpolation and demosaicing using lattice theory 有权
    使用晶格理论对图像插值和去马赛克进行误差分析

    公开(公告)号:US20070236580A1

    公开(公告)日:2007-10-11

    申请号:US11394836

    申请日:2006-03-31

    IPC分类号: H04N5/228

    CPC分类号: H04N9/045 G06T3/4015

    摘要: A spatial transformation methodology provides a new image interpolation scheme, or analyzes an already existing one. Examples of spatial operations include but are not limited to, demosaicing, edge enhancement or sharpening, linear filtering, and non-linear filtering. A demosaicing operation is described herein, although the scheme is applied generally to spatial transformation operations. The spatial transformation methodology includes detailed expressions for the noise covariance after a spatial operation is performed for each of the three color channels, red, green, and blue. A color filter array is in the form of a Bayer pattern and demosaicing is performed using a 4-neighbor bilinear interpolation. Using lattice theory, the spatial transformation methodology predicts noise covariance after demosaicing in terms of the input noise covariance and an autocorrelation function of the image is determined for a given selectable number of shifts.

    摘要翻译: 空间变换方法提供了一种新的图像插值方案,或分析了已有的图像插值方案。 空间操作的示例包括但不限于去马赛克,边缘增强或锐化,线性滤波和非线性滤波。 这里描述了去马赛克操作,尽管该方案通常应用于空间变换操作。 空间变换方法包括对三个颜色通道(红色,绿色和蓝色)中的每一个执行空间操作之后的噪声协方差的详细表达式。 滤色器阵列是拜耳图案的形式,并且使用四相双线性插值来执行去马赛克。 使用晶格理论,空间变换方法根据输入噪声协方差来预测去马赛克之后的噪声协方差,并且对于给定的可选择的移位数确定图像的自相关函数。

    System And Method For Efficiently Generating Device-Dependent Anaglyph Images
    6.
    发明申请
    System And Method For Efficiently Generating Device-Dependent Anaglyph Images 审中-公开
    有效地生成设备依赖的浮雕图像的系统和方法

    公开(公告)号:US20140218410A1

    公开(公告)日:2014-08-07

    申请号:US13759294

    申请日:2013-02-05

    IPC分类号: G06T15/00

    CPC分类号: H04N13/334

    摘要: A system for efficiently generating device-dependent anaglyph images includes a display device for presenting anaglyph images in a three-dimensional format. An anaglyph converter includes a conversion manager that interacts with system users to perform configuration procedures for generating anaglyph images. The configuration procedures are utilized to define one or more imaging parameters that are dependent upon imaging characteristics of said display device. The imaging parameters may include ghosting reduction parameters and color adjustment parameters. A processor device typically controls the conversion manager to perform the anaglyph image generation procedures.

    摘要翻译: 一种用于有效地产生装置相关的浮雕图像的系统包括用于以三维格式呈现浮雕图像的显示装置。 浮雕转换器包括与系统用户交互以执行用于生成浮雕图像的配置过程的转换管理器。 配置过程用于定义依赖于所述显示设备的成像特征的一个或多个成像参数。 成像参数可以包括重影减少参数和颜色调整参数。 处理器设备通常控制转换管理器执行浮雕图像生成过程。

    Super-resolution from 3D (3D to 2D conversion) for high quality 2D playback
    7.
    发明授权
    Super-resolution from 3D (3D to 2D conversion) for high quality 2D playback 有权
    从3D(3D到2D转换)的超分辨率,用于高质量的2D播放

    公开(公告)号:US08599240B2

    公开(公告)日:2013-12-03

    申请号:US12916212

    申请日:2010-10-29

    IPC分类号: H04N13/00

    摘要: A display is able to display 3D content in high resolution 2D by utilizing the many views contained in the 3D data and converting the 3D data into 2D data. In some embodiments, the 3D data is converted using shifts in different views of a pixel. In some embodiments, the 3D is converted using shifts in different views of a local pixel and global pixels as well. Displays implementing the 2D high resolution display in addition to a low resolution 3D display are able to display 3D and 2D data depending on a user's preference.

    摘要翻译: 通过利用3D数据中包含的许多视图并将3D数据转换为2D数据,显示器能够以高分辨率2D显示3D内容。 在一些实施例中,使用像素的不同视图中的偏移来转换3D数据。 在一些实施例中,使用局部像素和全局像素的不同视图中的偏移来转换3D。 除了低分辨率3D显示器之外,实现2D高分辨率显示的显示器能够根据用户的偏好显示3D和2D数据。

    SUPER-RESOLUTION FROM 3D (3D TO 2D CONVERSION) FOR HIGH QUALITY 2D PLAYBACK
    9.
    发明申请
    SUPER-RESOLUTION FROM 3D (3D TO 2D CONVERSION) FOR HIGH QUALITY 2D PLAYBACK 有权
    超级解决方案从3D(3D到2D转换)高质量二维回放

    公开(公告)号:US20120105582A1

    公开(公告)日:2012-05-03

    申请号:US12916212

    申请日:2010-10-29

    IPC分类号: H04N13/00

    摘要: A display is able to display 3D content in high resolution 2D by utilizing the many views contained in the 3D data and converting the 3D data into 2D data. In some embodiments, the 3D data is converted using shifts in different views of a pixel. In some embodiments, the 3D is converted using shifts in different views of a local pixel and global pixels as well. Displays implementing the 2D high resolution display in addition to a low resolution 3D display are able to display 3D and 2D data depending on a user's preference.

    摘要翻译: 通过利用3D数据中包含的许多视图并将3D数据转换为2D数据,显示器能够以高分辨率2D显示3D内容。 在一些实施例中,使用像素的不同视图中的偏移来转换3D数据。 在一些实施例中,使用局部像素和全局像素的不同视图中的偏移来转换3D。 除了低分辨率3D显示器之外,实现2D高分辨率显示的显示器能够根据用户的偏好显示3D和2D数据。

    SAFE MODE TRANSITION IN 3D CONTENT RENDERING
    10.
    发明申请
    SAFE MODE TRANSITION IN 3D CONTENT RENDERING 审中-公开
    三维内容渲染中的安全模式转换

    公开(公告)号:US20120068996A1

    公开(公告)日:2012-03-22

    申请号:US12887425

    申请日:2010-09-21

    IPC分类号: G06T15/00

    CPC分类号: G06T15/005

    摘要: A method for rendering 3D content in a safe mode includes receiving images to be rendered in a 3D format, and detecting, in the received images, at least one image having a 3D content creation or conversion error that creates an uncomfortable 3D effect to a user. The method may also include transitioning to a safe mode, under which 3D enhancement is performed to the detected at least one image to avoid the uncomfortable 3D effect, and rendering the 3D enhanced image for display.

    摘要翻译: 用于以安全模式呈现3D内容的方法包括接收要以3D格式呈现的图像,以及在接收到的图像中检测具有3D内容创建或转换错误的至少一个图像,其向用户产生不舒适的3D效果 。 该方法还可以包括转换到安全模式,在该模式下,对所检测的至少一个图像进行3D增强以避免不舒服的3D效果,以及渲染用于显示的3D增强图像。