利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

46 条记录 (耗时 0.015 秒)

    METHOD FOR GENERATING A MOTION FIELD FOR A VIDEO SEQUENCE
    31.
    发明公开
    METHOD FOR GENERATING A MOTION FIELD FOR A VIDEO SEQUENCE 审中-公开
    VERFAHREN ZUR ERZEUGUNG EINES BEWEGUNGSFELDESFÜREINE VIDEOSEQUENZ

    公开(公告)号：EP2954490A1

    公开(公告)日：2015-12-16

    申请号：EP14702296.6

    申请日：2014-02-04

    申请人： Thomson Licensing

    发明人： CONZE, Pierre-Henri ,  ROBERT, Philippe ,  CRIVELLI, Tomas ,  MORIN, Luce

    IPC分类号： G06T7/20

    CPC分类号： G06T7/2033 ,  G06T7/246 ,  G06T2207/10016 ,  G06T2207/20016 ,  G06T2207/20032 ,  G06T2207/30241 ,  H04N19/52 ,  H04N19/537 ,  H04N19/56 ,  H04N19/577 ,  H04N19/58

    摘要： The invention relates to a method for generating a motion field between a current frame and a reference frame belonging to a video sequence from an input set of motion fields. An motion field is associated to an ordered pair of frames comprises for a group of pixels belonging to a first frame of the ordered pair of frames, a motion vector computed from a location of the pixel in the first frame to an endpoint in a second frame of the ordered pair of frames. The method comprises a step for determining a plurality of motion paths from a current frame to a reference frame wherein a motion path comprises a sequence of N ordered pairs of frames associated to the input set of motion fields and wherein a first frame of an ordered pair corresponds to a second frame of the previous ordered pair in the sequence; the first image of the first ordered pair is the current frame; the second frame of the last ordered pair is the reference frame; and N is an integer. The method then comprises a step for determining, for the group of pixels belonging to the current frame, a plurality of candidate motion vectors from the current frame to the reference frame wherein a candidate motion vector is the result of a sum of motion vectors; each motion vector belonging to a motion field associated to an ordered pair of frames according to a determined motion path. And the method then comprises a step for selecting, for the group of pixels belonging to the current frame, a candidate motion vector among the plurality of candidate motion vectors.

    摘要翻译： 公开了一种从输入的运动场组合产生属于视频序列的当前帧与参考帧之间的运动场的方法。 运动场与有序的帧对相关联，包括属于有序对帧的第一帧的一组像素，从第一帧中的像素的位置到第二帧中的端点计算的运动矢量 的有序对框架。 该方法包括确定从当前帧到参考帧的多个运动路径，其中运动路径包括与运动场的输入集合相关联的N个有序对帧对的随机序列; N是整数。 该方法包括：对于属于当前帧的像素组，确定从当前帧到参考帧的多个候选运动矢量，其中候选运动矢量是运动矢量之和的结果; 每个运动矢量属于根据确定的运动路径与有序对帧对相关联的运动场。 然后，该方法包括为属于当前帧的像素组选择多个候选运动矢量中的运动矢量。

    METHOD AND DEVICE FOR ESTIMATING CAST SHADOW REGIONS AND/OR HIGHLIGHT REGIONS IN IMAGES
    38.
    发明公开
    METHOD AND DEVICE FOR ESTIMATING CAST SHADOW REGIONS AND/OR HIGHLIGHT REGIONS IN IMAGES 审中-公开
    用于估计图像中的投影阴影区域和/或高亮区域的方法和装置

    公开(公告)号：EP3319013A1

    公开(公告)日：2018-05-09

    申请号：EP16306441.3

    申请日：2016-11-03

    申请人： Thomson Licensing

    发明人： STAUDER, Jurgen ,  ROBERT, Philippe ,  GENDRON, David

    IPC分类号： G06K9/46 ,  G06T5/00 ,  H04N5/235 ,  G06K9/00

    CPC分类号： G06K9/4661 ,  G06K9/00664 ,  G06T5/007 ,  H04N5/2355

    摘要： The present invention relates to a method for estimating cast shadow regions and highlight regions in a scene, said scene being represented by a low dynamic range image, called LDR image, and a high dynamic range, called HDR image, said method comprising the steps of:
    - computing (S1) a detail map, called LDR detail map, of the LDR image, said LDR detail map associating a detail level to each pixel of the LDR image,
    - computing (S2) a detail map, called HDR detail map, of the HDR image, said HDR detail map associating a detail level to each pixel of the HDR image, and
    - detecting (S3) regions of the scene where the detail level in the HDR detail map is greater than the detail level in the LDR detail map, said detected regions corresponding to cast shadow regions or highlights region of the scene.

    摘要翻译： 本发明涉及一种用于估计场景中投影区域和高光区域的方法，所述场景由称为LDR图像的低动态范围图像和称为HDR图像的高动态范围表示，所述方法包括以下步骤： ： - 计算（S1）LDR图像的称为LDR细节图的细节图，所述LDR细节图将细节水平与LDR图像的每个像素相关联， - 计算（S2）称为HDR细节图的细节图， 所述HDR细节图将细节水平与HDR图像的每个像素相关联，以及 - 检测（S3）HDR细节图中的细节水平大于LDR细节中的细节水平的场景的区域 所述检测到的区域对应于场景的投影区域或高光区域。

    METHOD AND DEVICE FOR RENDERING AN IMAGE OF A SCENE COMPRISING A REAL OBJECT AND A VIRTUAL REPLICA OF THE REAL OBJECT
    40.
    发明公开
    METHOD AND DEVICE FOR RENDERING AN IMAGE OF A SCENE COMPRISING A REAL OBJECT AND A VIRTUAL REPLICA OF THE REAL OBJECT 审中-公开
    用于渲染包含真实对象和实际对象的虚拟副本的场景的图像的方法和设备

    公开(公告)号：EP3246879A1

    公开(公告)日：2017-11-22

    申请号：EP16305579.1

    申请日：2016-05-20

    申请人： Thomson Licensing

    发明人： FRADET, Matthieu ,  ROBERT, Philippe ,  LAURENT, Anthony

    IPC分类号： G06T15/04 ,  G06T11/00 ,  G06T19/00 ,  G06T19/20

    CPC分类号： G06T19/006 ,  G06T11/001 ,  G06T15/04 ,  G06T17/10 ,  G06T19/20 ,  G06T2219/2016 ,  G06T2219/2021

    摘要： A method and device for rendering a scene comprising one or more real objects. A virtual object is associated with each real object, a virtual object associated with a real object corresponding to a virtual replica of this real object. The virtual replica is used to render a transformation that may be applied to the real object when for example hit by a virtual object, the virtual object then replacing the corresponding real object within the scene. To bring realism to the scene, texture information obtained from image(s) of the real object(s) is used to texture the visible part(s) of the transformed virtual object(s). The texture information is selected in the images by using information on the visibility of the parts of the real object(s) that correspond to the visible parts of the transformed virtual object(s).

    摘要翻译： 一种用于渲染包括一个或多个真实对象的场景的方法和设备。 虚拟对象与每个真实对象相关联，虚拟对象与对应于该真实对象的虚拟复制品的真实对象相关联。 虚拟副本用于呈现可以应用于真实对象的变换，例如当被虚拟对象击中时，虚拟对象然后替换场景内的对应真实对象。 为了将现实主义带入现场，使用从真实物体的图像获得的纹理信息来纹理变换后的虚拟物体的可见部分。 通过使用关于对应于变换的虚拟对象的可见部分的真实对象的部分的可见性的信息来在图像中选择纹理信息。