公开(公告)号：EP4428826A1

公开(公告)日：2024-09-11

申请号：EP23160304.4

申请日：2023-03-06

申请人： Carl Zeiss Vision International GmbH

发明人： NÖLL, Tobias ,  EICHERT, Armin

IPC分类号： G06T17/20 ,  G06T15/04

CPC分类号： G06T2219/202420130101 ,  G06T19/20 ,  G06T17/00 ,  G06T15/04 ,  G06T7/564 ,  G06T17/205

摘要： Provided is a computer-implemented method being configured for generating a 3D representation (5) derived from an original 3D representation (1) of an object, the method comprising generating 2D images (3) of the original 3D representation comprising a silhouette map (31), respectively, wherein a pixel in the respective silhouette map (31) either belongs to the outer surface of the original 3D representation (1) or to a background, and generating (S2) the 3D representation (5) based on the generated silhouette maps (31).

公开(公告)号：EP3201884A4

公开(公告)日：2018-03-07

申请号：EP14903362

申请日：2014-09-30

申请人： CAE INC

发明人： LAGACÉ MICHEL ,  PICHÉ PATRICK

IPC分类号： G06T19/20 ,  G06T15/00 ,  G06T17/20 ,  G06T19/00

CPC分类号： G06T17/205 ,  G06F17/50 ,  G06F17/5009 ,  G06F17/5095 ,  G06T17/10 ,  G06T17/20 ,  G06T19/20 ,  G06T2210/21 ,  G06T2219/2021

摘要： A method and computer system for updating damaged-enhanced polygon meshes in a computer simulation associated to a storage module accessible to at least a first and a second decentralized simulation stations and a centralized processing unit thereof. At the first station, during the computer simulation, determining coordinates of a virtual impact on a 3D polygon mesh, computing newly formed 3D polygon mesh(es) from the virtual impact without updating the storage module and rendering damaged-enhanced image(s) of the newly formed 3D polygon mesh(es) for display from a first field of view of the first station. At the second station, receiving the coordinates of the virtual impact. At the centralized processing unit, receiving the coordinates of the virtual impact, computing the newly formed 3D polygon mesh(es) from the received coordinates independently from the first station, in non-real-time priority processing and persistently updating the storage module with newly formed 3D polygon mesh(es).

公开(公告)号：EP1779324B1

公开(公告)日：2018-01-17

申请号：EP05779725.0

申请日：2005-07-28

申请人： Koninklijke Philips N.V.

发明人： KAUS, Michael ,  MCNUTT, Todd, R. ,  PEKAR, Vladimir ,  MEYER, Matthias

IPC分类号： G06T7/00 ,  A61B6/00

CPC分类号： G06T7/12 ,  A61B6/00 ,  G06K9/6209 ,  G06T7/11 ,  G06T7/149 ,  G06T17/20 ,  G06T17/205 ,  G06T2207/10081 ,  G06T2207/20116 ,  G06T2207/30008 ,  G06T2207/30028

摘要： An image segmentation method segments a plurality of image features in an image. The plurality of image features are segmented non-simultaneously in succession. The segmenting of each image feature includes adapting an initial mesh to boundaries of the image feature. The segmenting of each image feature further includes preventing the adapted mesh from overlapping any previously adapted mesh.

公开(公告)号：EP3254237A1

公开(公告)日：2017-12-13

申请号：EP16773596.8

申请日：2016-01-18

申请人： Sony Corporation

发明人： LIU, Ming-Chang ,  SONG, Bi

IPC分类号： G06K9/46

CPC分类号： G06T11/003 ,  G06K9/4604 ,  G06K9/6267 ,  G06T7/0012 ,  G06T7/10 ,  G06T7/11 ,  G06T7/12 ,  G06T7/68 ,  G06T15/00 ,  G06T17/205 ,  G06T19/20 ,  G06T2207/10004 ,  G06T2207/10081 ,  G06T2207/10088 ,  G06T2207/20092 ,  G06T2207/30016 ,  G06T2219/028

摘要： An apparatus and method for performing automatic 3D image segmentation and reconstruction of organ structures, which is particularly well-suited for use on cortical surfaces is presented. A brain extraction process removes non-brain image elements, then classifies brain tissue as to type in preparation for a cerebrum segmentation process that determines which portions of the image information belong to specific physiological structures. Ventricle filling is performed on the image data based on information from a ventricle extraction process. A reconstruction process follows in which specific surfaces, such as white matter (WM) and grey matter (GM), are reconstructed.

公开(公告)号：EP3249928A1

公开(公告)日：2017-11-29

申请号：EP16305592.4

申请日：2016-05-23

申请人： Thomson Licensing

发明人： LASSERRE, Sébastien ,  GALPIN, Franck ,  ANDRIVON, Pierre

IPC分类号： H04N21/2343 ,  G06T3/00 ,  H04N19/70

CPC分类号： H04N21/234327 ,  A63F2300/8082 ,  G06F3/012 ,  G06F3/04815 ,  G06T3/0087 ,  G06T3/0093 ,  G06T15/205 ,  G06T17/205 ,  G06T19/006 ,  G06T19/20 ,  G06T2219/2004 ,  G10L19/008 ,  H04H20/95 ,  H04N19/70 ,  H04N21/23439

摘要： The present disclosure relates to methods, apparatus or systems for generating, transmitting and decoding a backward compatible immersive video stream. The stream is carrying data representative of an immersive video, composed of a frame organized according to a layout comprising a first area (51) encoded according to a rectangle mapping, a second area (52) encoded according to a mapping transitory from the rectangular mapping to an immersive mapping and a third area (53) encoded according to the immersive mapping. In order to be backward compatible, the stream further comprises a first information representative of the size and the location of the first area within the video frame, and a second information comprising at least the type of the selected layout, the field of view of first part, of the size of said second area within the video frame and a reference direction.

摘要翻译： 本公开涉及用于生成，发送和解码后向兼容拟真视频流的方法，装置或系统。 该流携带表示根据包括根据矩形映射编码的第一区域（51）和根据矩形映射过渡的映射编码的第二区域（52）的布局组成的表示沉浸式视频的数据 到沉浸式映射和根据沉浸式映射编码的第三区域（53）。 为了向后兼容，该流还包括表示视频帧内的第一区域的大小和位置的第一信息，以及至少包括所选择的布局的类型，第一视野 部分视频帧内的所述第二区域的大小和参考方向。

公开(公告)号：EP3226212A4

公开(公告)日：2017-10-04

申请号：EP15863391

申请日：2015-11-27

申请人： PANASONIC IP MAN CO LTD

发明人： YAMAMOTO HARUMI ,  HORII TOSHIHIDE

IPC分类号： G06T17/20 ,  G06T1/00

CPC分类号： G06T15/005 ,  G06T1/00 ,  G06T17/20 ,  G06T17/205 ,  G06T2210/04 ,  G06T2215/16

摘要： An object of the present invention would be to determine an accurate shape model even if measurement points of only part of a surface are obtained. The modeling device (10) according to the present invention includes a data obtainer (11), a surface extractor (12), and a modeler (13). The surface extractor (12) determines, by use of mathematical formulae representing a first surface (3) and second surfaces (3) surrounding the first surface (3), of the three-dimensional object (30), boundaries surrounding the first surface (3). The surface extractor (12) extracts, from measurement points belonging to the first surface (3), measurement points relating to a region (D1) inside the first surface (3) and having a predetermined width (W1) from the boundaries.

摘要翻译： 本发明的目的是即使仅获得表面的一部分的测量点，也能够确定准确的形状模型。 根据本发明的建模装置（10）包括数据获取器（11），表面提取器（12）和建模器（13）。 表面提取器（12）通过使用表示围绕第一表面（3）的第一表面（3）和第二表面（3）的数学公式确定三维物体（30），围绕第一表面 3）。 表面提取器（12）从属于第一表面（3）的测量点提取与第一表面（3）内部的区域（D1）相关并且具有距边界的预定宽度（W1）的测量点。

公开(公告)号：EP3158535A1

公开(公告)日：2017-04-26

申请号：EP14895424.1

申请日：2014-06-20

申请人： Intel Corporation

发明人： PARK, Minje ,  DUCHENNE, Olivier ,  CHEON, Yeongjae ,  KIM, Tae-Hoon ,  SHEN, Xiaolu ,  DU, Yangzhou ,  RYU, Wooju ,  JU, Myung-Ho

IPC分类号： G06T15/08

CPC分类号： G06T17/205 ,  G06K9/00208 ,  G06K9/00214 ,  G06K9/00221 ,  G06K9/00248 ,  G06K9/00261 ,  G06K9/00281 ,  G06T7/251 ,  G06T17/20 ,  G06T2200/04 ,  G06T2207/30201

摘要： Apparatuses, methods and storage medium associated with 3D face model reconstruction are disclosed herein. In embodiments, an apparatus may include a facial landmark detector, a model fitter and a model tracker. The facial landmark detector may be configured to detect a plurality of landmarks of a face and their locations within each of a plurality of image frames. The model fitter may be configured to generate a 3D model of the face from a 3D model of a neutral face, in view of detected landmarks of the face and their locations within a first one of the plurality of image frames. The model tracker may be configured to maintain the 3D model to track the face in subsequent image frames, successively updating the 3D model in view of detected landmarks of the face and their locations within each of successive ones of the plurality of image frames. In embodiments, the facial landmark detector may include a face detector, an initial facial landmark detector, and one or more facial landmark detection linear regressors. Other embodiments may be described and/or claimed.

摘要翻译： 本文公开了与3D人脸模型重建相关联的设备，方法和存储介质。 在实施例中，装置可以包括面部标志检测器，模型拟合器和模型跟踪器。 面部标志检测器可以被配置为检测多个图像帧中的每一个内的面部的多个界标及其位置。 鉴于在多个图像帧中的第一个图像帧内检测到的面部标记和它们的位置，模型拟合器可以被配置为从中性面部的3D模型生成面部的3D模型。 模型跟踪器可以被配置为保持3D模型以跟踪后续图像帧中的面部，考虑到检测到的面部标志以及它们在多个图像帧的每个连续图像帧内的位置来连续地更新3D模型。 在实施例中，面部标志检测器可以包括面部检测器，初始面部标志检测器以及一个或多个面部标志检测线性回归器。 其他实施例可以被描述和/或要求保护。

公开(公告)号：EP3101626A1

公开(公告)日：2016-12-07

申请号：EP16171751.7

申请日：2016-05-27

申请人： Imagination Technologies Limited

发明人： LACEY, Peter ,  FENNEY, Simon

IPC分类号： G06T17/20

CPC分类号： G06T17/20 ,  G06T15/005 ,  G06T17/205

摘要： A tessellation method is described which uses tessellation factors defined for each vertex of a patch which may be a quad, a triangle or an isoline. The method is implemented in a computer graphics system and involves comparing the vertex tessellation factors to a threshold. If the vertex tessellation factors for either a left vertex or a right vertex, which define an edge of an initial patch, exceed the threshold, the edge is sub-divided by the addition of a new vertex which divides the edge into two parts and two new patches are formed. New vertex tessellation factors are calculated for each vertex in each of the newly formed patches, both of which include the newly added vertex. The method is then repeated for each of the newly formed patches until none of the vertex tessellation factors exceed the threshold.

摘要翻译： 描述了一种镶嵌方法，其使用为可以是四边形，三角形或等值线的贴片的每个顶点定义的镶嵌因子。 该方法在计算机图形系统中实现，并且涉及将顶点镶嵌因子与阈值进行比较。 如果定义一个初始贴片边缘的左顶点或右顶点的顶点镶嵌因子超过阈值，则边缘被添加一个新的顶点进行细分，该顶点将边缘分成两部分 形成新的补丁。 为每个新形成的贴片中的每个顶点计算新的顶点镶嵌因子，其中包括新添加的顶点。 然后对于每个新形成的补丁重复该方法，直到顶点细分因子都不超过阈值。

公开(公告)号：EP2973421A1

公开(公告)日：2016-01-20

申请号：EP14713886.1

申请日：2014-03-10

申请人： Creative Edge Software LLC

发明人： JENNINGS, Amy ,  JENNINGS, Stuart

IPC分类号： G06T15/04

CPC分类号： G06T15/04 ,  G06T11/001 ,  G06T15/20 ,  G06T17/10 ,  G06T17/205 ,  G06T19/00 ,  G06T2200/21 ,  G06T2210/52 ,  G06T2219/016

摘要： A method and apparatus are provided for applying a two-dimensional image on a three- dimensional model, the three-dimensional model composed of a polygonal mesh. The method comprises the steps of generating an adjacency structure for all triangles within the polygon mesh, identifying a triangle within membrane containing the desired centre point of the label, calculating spatial distances between the three vertices of the triangle and desired centre point of the label; checking each triangle edge to see if the calculated distances show an intersection on the two-dimensional image, if a collision is detected add the neighbouring triangle to the list of triangles to process and iteratively processing all the triangles in the list until the list is empty; calculate the spatial data of the single unknown vertex within the triangle, check the two edges of the triangle to see if the calculated distances show an intersection with the two-dimensional image, if an intersection occurs add this new triangle neighbour to the triangle list; transforming the points and spatial data into UV-coordinates; and applying the two-dimensional image to the three-dimensional model using the UV-coordinates. Transforming the points and spatial data into UV-coordinates; and applying the two- dimensional image to the three-dimensional model using the UV-coordinates.

公开(公告)号：EP2950276A1

公开(公告)日：2015-12-02

申请号：EP15165566.9

申请日：2015-04-29

申请人： Rolls-Royce plc

发明人： Date, David ,  Bates, Ronald

IPC分类号： G06T17/20 ,  G06T19/20 ,  G06F17/50

CPC分类号： G06T17/20 ,  G06F17/5018 ,  G06T17/205 ,  G06T19/20 ,  G06T2219/2021

摘要： A method is provided of generating a customised finite element mesh for a component which is an actual example of a nominal component represented by a generic finite element mesh, the actual component displaying shape variation relative to the generic finite element mesh. The method includes steps of: providing the generic finite element mesh; providing a library of displacement shapes of the generic mesh, each displacement shape being applicable to the generic mesh to generate an altered mesh; providing a set of scanned data points which map the surface of the actual component, each scanned data point defining the spatial position of a respective location on the surface of the actual component; superposing the scanned data points on the surface of the generic mesh; projecting the scanned data points onto respective proximal surface locations of the generic mesh to form a set of near data points, each near data point defining the spatial position of the respective location on the surface of the generic mesh; determining a combination of the displacement shapes which substantially removes the shape variation by reducing or eliminating deviations between scanned data points and their corresponding near data points; and applying the combination of displacement shapes to the generic mesh to generate a customised finite element mesh for the actual component.

摘要翻译： 提供了一种生成用于组件的定制的有限元网格的方法，该组件是由通用有限元网格表示的标称组件的实际示例，实际组件显示相对于通用有限元网格的形状变化。 该方法包括以下步骤：提供通用有限元网格; 提供通用网格的位移形状库，每个位移形状可应用于通用网格以生成改变的网格; 提供映射实际部件表面的一组扫描数据点，每个扫描数据点定义实际部件表面上相应位置的空间位置; 将扫描的数据点叠加在通用网格的表面上; 将扫描的数据点投影到通用网格的各个近端表面位置上以形成一组近数据点，每个近数据点定义通用网格表面上相应位置的空间位置; 通过减少或消除扫描数据点与其对应的近数据点之间的偏差来确定基本上去除形状变化的位移形状的组​​合; 以及将位移形状的组​​合应用于通用网格以为实际部件生成定制的有限元网格。