公开(公告)号：US20120162216A1

公开(公告)日：2012-06-28

申请号：US13334610

申请日：2011-12-22

申请人： Do-Hyung KIM ,  Ji-Hyung LEE ,  Bon-Ki KOO

发明人： Do-Hyung KIM ,  Ji-Hyung LEE ,  Bon-Ki KOO

IPC分类号： G06T15/00

CPC分类号： G02B27/2278 ,  H04N13/388

摘要： The present invention provides a cylindrical three-dimensional (3D) image display apparatus and method. The cylindrical 3D image display apparatus includes a spiral screen unit configured such that a plurality of individual screens, each being spirally formed, form a shape of a cylinder, and such that the spiral screen unit display an image on the cylinder. A 3D image control unit is configured to display a 3D image by controlling transparency of each of the plurality of individual screens, based on a display sequence of slice images of the 3D image projected from above or below the cylinder.

摘要翻译： 本发明提供一种圆柱形三维（3D）图像显示装置和方法。 圆柱形3D图像显示装置包括螺旋屏单元，其被构造为使得多个单独的屏幕（各自螺旋形地形成）形成圆柱体的形状，并且使得螺旋屏幕单元在圆筒上显示图像。 3D图像控制单元被配置为基于从气缸上方或下方突出的3D图像的切片图像的显示顺序，通过控制多个单独屏幕中的每一个的透明度来显示3D图像。

公开(公告)号：US20120163675A1

公开(公告)日：2012-06-28

申请号：US13335120

申请日：2011-12-22

申请人： Han-Byul JOO ,  Seong-Jae LIM ,  Ji-Hyung LEE ,  Bon-Ki KOO

发明人： Han-Byul JOO ,  Seong-Jae LIM ,  Ji-Hyung LEE ,  Bon-Ki KOO

IPC分类号： G06K9/00

CPC分类号： G06T7/251 ,  G06T7/13 ,  G06T2207/20044

摘要： Disclosed herein is a motion capture apparatus and method. The motion capture apparatus includes a three-dimensional (3D) appearance reconstruction unit for reconstructing a 3D appearance of an entity using a multi-view image obtained by capturing the entity at a T+1-th frame. A 3D skeleton generation unit generates a 3D skeleton of the T+1-th frame using the 3D appearance and a model of the entity having a motion of a T-th frame. A motion reconstruction unit reconstructs a motion of the T+1-th frame of the model by changing the motion of the model based on the 3D skeleton of the T+1-th frame.

摘要翻译： 这里公开了一种运动捕捉装置和方法。 运动捕捉装置包括三维（3D）外观重建单元，用于使用通过在第T + 1帧捕获实体而获得的多视图图像来重构实体的3D外观。 3D骨架生成单元使用3D外观和具有第T帧的运动的实体的模型来生成第T + 1帧的3D骨架。 运动重建单元通过基于第T + 1帧的3D骨架改变模型的运动来重建模型的第T + 1帧的运动。

公开(公告)号：US20120147004A1

公开(公告)日：2012-06-14

申请号：US13324581

申请日：2011-12-13

申请人： Yoon-Seok CHOI ,  Ji-Hyung LEE ,  Bon-Ki KOO

发明人： Yoon-Seok CHOI ,  Ji-Hyung LEE ,  Bon-Ki KOO

IPC分类号： G06T13/00 ,  G06T17/00 ,  G09G5/00

CPC分类号： G06T13/40 ,  G06T15/04

摘要： Disclosed herein is an apparatus for generating a digital actor based on multiple images. The apparatus includes a reconstruction appearance generation unit, a texture generation unit, and an animation assignment unit. The reconstruction appearance generation unit generates a reconstruction model in which the appearance of a target object is reconstructed in such a way as to extract 3-Dimensional (3D) geometrical information of the target object from images captured using multiple cameras which are provided in directions which are different from each other. The texture generation unit generates a texture image for the reconstruction model based on texture coordinates information calculated based on the reconstruction model. The animation assignment unit allocates an animation to each joint of the reconstruction model, which has been completed by applying the texture image to the reconstruction model, in such a way as to add motion data to the joint.

摘要翻译： 本文公开了一种用于基于多个图像生成数字演员的装置。 该装置包括重建外观生成单元，纹理生成单元和动画分配单元。 重建外观生成单元生成重构模型，其中以从多个摄像机拍摄的图像中提取目标对象的三维（3D）几何信息来重构目标对象的外观，其中， 是不同的。 纹理生成单元基于基于重构模型计算的纹理坐标信息生成用于重建模型的纹理图像。 动画分配单元通过将纹理图像应用于重建模型来完成的重建模型的每个关节，以将运动数据添加到关节。

公开(公告)号：US20120162218A1

公开(公告)日：2012-06-28

申请号：US13335668

申请日：2011-12-22

申请人： Ho-Won KIM ,  Bon-Ki KOO ,  Seung-Wook LEE

发明人： Ho-Won KIM ,  Bon-Ki KOO ,  Seung-Wook LEE

IPC分类号： G06T15/00

CPC分类号： G06T19/00 ,  G06T13/40

摘要： Disclosed herein is technology for generating a digital clone. An apparatus for generating a digital clone includes a standard human body model generation unit for extracting information about appearance deformations based on joint control angles of joints from posture-based appearance deformation examples, generating a parametric shape control engine in which the appearance deformation information is incorporated, and incorporating the parametric shape control engine in a standard mesh-type human body model, thus generating a standard human body model. A unique human body model generation unit receives multi-view image examples based on a change in a posture of an actor, generates a 3D model of the actor based on multi-view image examples, and transfers the standard human body model to the 3D model, thus generating a unique human body model, in which unique appearance deformations of the actor based on the change in the posture of the actor are reflected.

摘要翻译： 这里公开了用于生成数字克隆的技术。 一种用于生成数字克隆的装置包括：标准人体模型生成单元，用于基于来自基于姿势的外观变形例的关节的关节控制角度提取关于外观变形的信息，生成其中包含外观变形信息的参数化形状控制引擎 ，并将参数化形状控制引擎并入标准网格型人体模型中，从而产生标准人体模型。 独特的人体模型生成单元基于演员姿势的变化接收多视点图像示例，基于多视图图像示例生成演员的3D模型，并将标准人体模型转移到3D模型 ，从而产生独特的人体模型，其中反映了基于演员姿势变化的演员的独特外观变形。

公开(公告)号：US20120162441A1

公开(公告)日：2012-06-28

申请号：US13221307

申请日：2011-08-30

申请人： Jae-Hean KIM ,  Bon-Ki KOO

发明人： Jae-Hean KIM ,  Bon-Ki KOO

IPC分类号： H04N17/06

CPC分类号： G06T7/80

摘要： Disclosed herein is a camera calibration apparatus. The camera calibration apparatus includes an image reception unit and a camera calibration unit. The image reception unit receives images, in which a same background is captured, from respective cameras placed at locations which are different from each other. The camera calibration unit calculates an entire matrix using canonic topographies for all parallelograms located on respective surfaces which are different from each other within each of the images, and calculates infinite hymnographies between the cameras using the entire matrix at the same time.

摘要翻译： 这里公开了一种相机校准装置。 相机校准装置包括图像接收单元和相机校准单元。 图像接收单元从放置在彼此不同的位置的各个照相机接收与其相同背景的图像。 相机校准单元使用位于相应表面上的所有平行四边形的正交地形来计算整个矩阵，所述平行四边形在每个图像内彼此不同，并且在同一时间使用整个矩阵计算摄像机之间的无限气象。

公开(公告)号：US20120162412A1

公开(公告)日：2012-06-28

申请号：US13335859

申请日：2011-12-22

申请人： Ho-Won KIM ,  Hyun KANG ,  Seung-Wook LEE ,  Bon-Ki KOO

发明人： Ho-Won KIM ,  Hyun KANG ,  Seung-Wook LEE ,  Bon-Ki KOO

IPC分类号： H04N7/18 ,  G06K9/62

CPC分类号： G06T7/174 ,  G06T7/11 ,  G06T7/194 ,  G06T2207/10012

摘要： Disclosed herein are an image matting apparatus using multiple cameras and a method of generating alpha maps. The apparatus includes a multi-camera unit, a depth estimation unit, an alpha map estimation unit, and an image matting unit. The multi-camera unit acquires a main image generated when a main camera captures an object at a specific camera angle, and acquires a plurality of sub-images generated when a sub-camera captures the object at different camera angles. The depth estimation unit estimates a depth value, corresponding to a distance between the main camera and the object, for each cluster. The alpha map estimation unit estimates an alpha map of the main image using the depth value estimated by the depth estimation unit. The image matting unit extracts a foreground from the main image using the alpha map, and performs image matting using the extracted foreground.

摘要翻译： 这里公开了使用多个照相机的图像消光装置和产生α映射的方法。 该装置包括多摄像机单元，深度估计单元，阿尔法地图估计单元和图像消光单元。 多摄像机单元获取当主摄像机以特定摄像机角度拍摄对象时产生的主图像，并且获取当副摄像机以不同的摄像机角度捕获对象时生成的多个子图像。 深度估计单元针对每个簇估计对应于主摄像机和对象之间的距离的深度值。 α图估计单元使用由深度估计单元估计的深度值来估计主图像的α图。 图像消光单元使用α图从主图像提取前景，并使用提取的前景执行图像消隐。

公开(公告)号：US20120162226A1

公开(公告)日：2012-06-28

申请号：US13331868

申请日：2011-12-20

申请人： Seung-Hyup SHIN ,  Soon-Hyoung PYO ,  Bon-Ki KOO

发明人： Seung-Hyup SHIN ,  Soon-Hyoung PYO ,  Bon-Ki KOO

IPC分类号： G06T17/20

CPC分类号： G06T13/60 ,  G06T17/205

摘要： Disclosed herein is a fracture pattern generation apparatus for a crumbling effect includes a graph generation unit, a fragment center setting unit, a fracture pattern generation unit, and a fragment mesh generation unit. The graph generation unit generates the graph of the mesh model by filling the inside of a mesh model with a plurality of vertices and connecting the vertices using line segments. The fragment center setting unit sets the central vertices of fragments, which are separated due to fractures, from among the plurality of vertices formed on the graph. The fracture pattern generation unit generates the fracture pattern by setting the central vertices of the fragments to terminal vertices of the fracture pattern and allocating Identifications (IDs) to the respective the central vertices of fragments. The fragment mesh generation unit generates fragment meshes by performing division on the graph based on the fracture pattern.

摘要翻译： 本文公开了一种用于破碎效果的断裂图形生成装置，包括图形生成单元，碎片中心设置单元，断裂图案生成单元和碎片网格生成单元。 图形生成单元通过用多个顶点填充网格模型的内部并使用线段连接顶点来生成网格模型的图形。 片段中心设置单元从形成在图形上的多个顶点之中设置由于断裂而分离的碎片的中心顶点。 断裂图案生成单元通过将碎片的中心顶点设置为断裂图案的末端顶点并将识别（ID）分配给各个片段的中心顶点来生成断裂图案。 片段网格生成单元通过基于断裂图案对图形进行分割来生成片段网格。