中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

10 records (took 0.029 seconds)

    TECHNIQUES FOR NAVIGATION AMONG MULTIPLE IMAGES
    1.
    发明申请
    TECHNIQUES FOR NAVIGATION AMONG MULTIPLE IMAGES 审中-公开
    多图像导航技术

    公开(公告)号：US20150109328A1

    公开(公告)日：2015-04-23

    申请号：US14056505

    申请日：2013-10-17

    Applicant: Google Inc.

    Inventor： David Gallup ,  Steven Maxwell Seitz

    IPC: G06F3/0484

    CPC classification number: G06F3/0488

    Abstract: Aspects of the disclosure relate generally to providing a user with an image navigation experience. In order to do so, a reference image may be identified. A set of potential target images for the reference image may also be identified. An area of the reference image is identified. For each particular image of the set of potential target images an associated cost for the identified area is determined based at least in part on a cost function for transitioning between the reference image and the particular target image. A target image is selected for association with the identified area based on the determined associated cost functions.

    Abstract translation: 本公开的方面通常涉及为用户提供图像导航体验。 为了这样做，可以识别参考图像。 还可以识别用于参考图像的一组潜在目标图像。 识别参考图像的区域。 对于潜在目标图像集合的每个特定图像，至少部分地基于用于在参考图像和特定目标图像之间转换的成本函数来确定所识别区域的相关联的成本。 基于所确定的相关联的成本函数，选择目标图像以与所识别的区域相关联。

    MULTI-VIEW SCENE FLOW STITCHING
    2.
    发明申请
    MULTI-VIEW SCENE FLOW STITCHING 审中-公开

    公开(公告)号：US20180192033A1

    公开(公告)日：2018-07-05

    申请号：US15395355

    申请日：2016-12-30

    Applicant: Google Inc.

    Inventor： David Gallup ,  Johannes Schönberger

    IPC: H04N13/02

    CPC classification number: H04N13/243 ,  G06T3/0062 ,  G06T3/4038 ,  G06T7/38 ,  G06T2207/10021 ,  H04N5/23238 ,  H04N5/247 ,  H04N13/111 ,  H04N13/271 ,  H04N13/275 ,  H04N13/282 ,  H04N13/296

    Abstract: A method of multi-view scene flow stitching includes capture of imagery from a three-dimensional (3D) scene by a plurality of cameras and stitching together captured imagery to generate virtual reality video that is both 360-degree panoramic and stereoscopic. The plurality of cameras capture sequences of video frames, with each camera providing a different viewpoint of the 3D scene. Each image pixel of the sequences of video frames is projected into 3D space to generate a plurality of 3D points. By optimizing for a set of synchronization parameters, stereoscopic image pairs may be generated for synthesizing views from any viewpoint. In some embodiments, the set of synchronization parameters includes a depth map for each of the plurality of video frames, a plurality of motion vectors representing movement of each one of the plurality of 3D points in 3D space over a period of time, and a set of time calibration parameters.

    Depth map generation
    4.
    发明授权
    Depth map generation 有权
    深度图生成

    公开(公告)号：US08760500B1

    公开(公告)日：2014-06-24

    申请号：US14061423

    申请日：2013-10-23

    Applicant: Google Inc.

    Inventor： David Gallup ,  Fu Yu ,  Steven Maxwell Seitz

    IPC: H04N13/02 ,  H04N7/18 ,  H04N13/00

    CPC classification number: H04N13/271 ,  G06T7/579 ,  G06T2207/10016 ,  G06T2207/30244

    Abstract: Aspects of the disclosure relate generally to generating depth data from a video. As an example, one or more computing devices may receive an initialization request for a still image capture mode. After receiving the request to initialize the still image capture mode, the one or more computing devices may automatically begin to capture a video including a plurality of image frames. The one or more computing devices track features between a first image frame of the video and each of the other image frames of the video. Points corresponding to the tracked features may be generated by the one or more computing devices using a set of assumptions. The assumptions may include a first assumption that there is no rotation and a second assumption that there is no translation. The one or more computing devices then generate a depth map based at least in part on the points.

    Abstract translation: 本公开的方面通常涉及从视频生成深度数据。 作为示例，一个或多个计算设备可以接收静态图像捕获模式的初始化请求。 在接收到初始化静止图像捕获模式的请求之后，一个或多个计算设备可以自动开始捕获包括多个图像帧的视频。 一个或多个计算设备跟踪视频的第一图像帧和视频的每个其他图像帧之间的特征。 与被跟踪的特征相对应的点可以由一个或多个计算设备使用一组假设来生成。 这些假设可以包括没有旋转的第一假设和没有平移的第二假设。 然后，一个或多个计算设备至少部分地基于点生成深度图。

    TECHNIQUES FOR NAVIGATION AMONG MULTIPLE IMAGES
    5.
    发明申请
    TECHNIQUES FOR NAVIGATION AMONG MULTIPLE IMAGES 有权
    多图像导航技术

    公开(公告)号：US20150113474A1

    公开(公告)日：2015-04-23

    申请号：US14056527

    申请日：2013-10-17

    Applicant: GOOGLE INC.

    Inventor： David Gallup ,  Liyong Chen ,  Shuchang Zhou ,  Steven Maxwell Seitz

    IPC: G06F3/0485

    CPC classification number: G06F3/0485 ,  G06F3/04845

    Abstract: Aspects of the disclosure relate generally to providing a user with an image navigation experience. In order to do so, a reference image may be identified. A set of potential target images for the reference image may also be identified. A drag vector for user input relative to the reference image is determined. For particular image of the set of target images an associated cost is determined based at least in part on a cost function and the drag vector. A target image is selected based on the determined associated costs.

    Abstract translation: 本公开的方面通常涉及为用户提供图像导航体验。 为了这样做，可以识别参考图像。 还可以识别用于参考图像的一组潜在目标图像。 确定用于相对于参考图像的用户输入的拖动矢量。 对于目标图像集合的特定图像，至少部分地基于成本函数和拖动矢量确定相关联的成本。 基于确定的相关成本来选择目标图像。

    DEPTH MAP GENERATION
    6.
    发明申请
    DEPTH MAP GENERATION 审中-公开
    深度地图生成

    公开(公告)号：US20150109416A1

    公开(公告)日：2015-04-23

    申请号：US14278471

    申请日：2014-05-15

    Applicant: Google Inc.

    Inventor： David Gallup ,  Fu Yu ,  Steven Maxwell Seitz

    IPC: H04N13/02

    Abstract: Aspects of the disclosure relate generally to generating depth data from a video. As an example, one or more computing devices may receive an initialization request for a still image capture mode. After receiving the request to initialize the still image capture mode, the one or more computing devices may automatically begin to capture a video including a plurality of image frames. The one or more computing devices track features between a first image frame of the video and each of the other image frames of the video. Points corresponding to the tracked features may be generated by the one or more computing devices using a set of assumptions. The assumptions may include a first assumption that there is no rotation and a second assumption that there is no translation. The one or more computing devices then generate a depth map based at least in part on the points.

    Abstract translation: 本公开的方面通常涉及从视频生成深度数据。 作为示例，一个或多个计算设备可以接收静态图像捕获模式的初始化请求。 在接收到初始化静止图像捕获模式的请求之后，一个或多个计算设备可以自动开始捕获包括多个图像帧的视频。 一个或多个计算设备跟踪视频的第一图像帧和视频的每个其他图像帧之间的特征。 与被跟踪的特征相对应的点可以由一个或多个计算设备使用一组假设来生成。 这些假设可以包括没有旋转的第一假设和没有平移的第二假设。 然后，一个或多个计算设备至少部分地基于点生成深度图。

    CAPTURE AND RENDER OF PANORAMIC VIRTUAL REALITY CONTENT
    9.
    发明申请
    CAPTURE AND RENDER OF PANORAMIC VIRTUAL REALITY CONTENT 审中-公开
    全景虚拟现实内容的捕捉和渲染

    公开(公告)号：US20160353089A1

    公开(公告)日：2016-12-01

    申请号：US14723151

    申请日：2015-05-27

    Applicant: GOOGLE INC.

    Inventor： David Gallup ,  Robert Anderson ,  Carlos Hernandez Esteban ,  Steven Maxwell Seitz ,  Riley Adams

    IPC: H04N13/04 ,  G02B27/01 ,  G06T19/00

    CPC classification number: H04N13/344 ,  G02B27/017 ,  G02B27/0172 ,  G02B2027/011 ,  G02B2027/0138 ,  G02B2027/014 ,  G02B2027/0187 ,  G06T15/205 ,  H04N13/111 ,  H04N13/161 ,  H04N13/194 ,  H04N13/211 ,  H04N13/239 ,  H04N13/243 ,  H04N13/296 ,  H04N13/366

    Abstract: Systems and methods are described for defining a set of images based on captured images, receiving a viewing direction associated with a user of a virtual reality (VR) head mounted display, receiving an indication of a change in the viewing direction. The methods further include configuring, a re-projection of a portion of the set of images, the re-projection based at least in part on the changed viewing direction and a field of view associated with the captured images, and converting the portion from a spherical perspective projection into a planar perspective projection, rendering by the computing device and for display in the VR head mounted display, an updated view based on the re-projection, the updated view configured to correct distortion and provide stereo parallax in the portion, and providing, to the head mounted display, the updated view including a stereo panoramic scene corresponding to the changed viewing direction.

    Abstract translation: 描述了基于捕获的图像来定义一组图像的系统和方法，接收与虚拟现实（VR）头戴式显示器的用户相关联的观看方向，接收观看方向的改变的指示。 所述方法还包括至少部分地基于所改变的观察方向和与所捕获图像相关联的视场来配置，所述图像集合的一部分的重新投影，所述重新投影将所述部分从 球面透视投影到平面透视投影中，由计算设备渲染并用于显示在VR头戴式显示器中，基于重新投影的更新视图，配置为校正失真并在该部分中提供立体视差的更新视图，以及 向头戴式显示器提供包括与改变的观看方向对应的立体全景场景的更新视图。

    Techniques for navigation among multiple images
    10.
    发明授权
    Techniques for navigation among multiple images 有权
    技术在多个图像之间导航

    公开(公告)号：US09046996B2

    公开(公告)日：2015-06-02

    申请号：US14056527

    申请日：2013-10-17

    Applicant: Google Inc.

    Inventor： David Gallup ,  Liyong Chen ,  Shuchang Zhou ,  Steven Maxwell Seitz

    IPC: G09G5/10 ,  G06F3/0485

    CPC classification number: G06F3/0485 ,  G06F3/04845

    Abstract: Aspects of the disclosure relate generally to providing a user with an image navigation experience. In order to do so, a reference image may be identified. A set of potential target images for the reference image may also be identified. A drag vector for user input relative to the reference image is determined. For particular image of the set of target images an associated cost is determined based at least in part on a cost function and the drag vector. A target image is selected based on the determined associated costs.

    Abstract translation: 本公开的方面通常涉及为用户提供图像导航体验。 为了这样做，可以识别参考图像。 还可以识别用于参考图像的一组潜在目标图像。 确定用于相对于参考图像的用户输入的拖动矢量。 对于目标图像集合的特定图像，至少部分地基于成本函数和拖动矢量确定相关联的成本。 基于确定的相关成本来选择目标图像。

Patent Agency Ranking