Abstract: An apparatus for detecting a pose in motion capture data includes: a motion data input unit which receives motion data of characters; a virtual marker attaching unit for forming a point cloud by attaching virtual markers to joints of an end-effector of each character; and a scaling unit for, when a frame has different character size from an a character size of an original frame to be compared is detected, scaling the character size. The apparatus further includes an ICP algorithm execution unit for finding a matching transformation matrix between the original frame and each frame of the motion data, of which character size has been scaled, by applying an ICP algorithm, and determining a frame, in which character's pose has the smallest difference from that in the original frame based on a sum of the distances between the virtual markers chosen by sampling the matched two poses.

Abstract: A dynamics-based motion generation apparatus includes: a dynamics model conversion unit for automatically converting character model data into dynamics model data of a character to be subjected to a dynamics simulation; a dynamics model control unit for modifying the dynamics model data and adding or modifying an environment model; a dynamics motion conversion unit for automatically converting reference motion data of the character, which has been created by using the character model data, into dynamics motion data through the dynamics simulation by referring to the dynamics model data and the environment model; and a motion editing unit for editing the reference motion data to decrease a gap between reference motion data and dynamics motion data. The apparatus further includes a robot motion control unit for controlling a robot by inputting preset torque values to related joint motors of the robot by referring to the dynamics motion data.

Abstract: A digital image photographing method includes: recognizing a subject by analyzing an image photographed by a digital image photographing apparatus; separating the recognized subject from a background in the image; and displaying a recommending lead line of a rule of thirds on a display of the digital image photographing apparatus to help position the recognized subject on an intersection point of transversal and vertical trisectional lines. Further, the digital image photographing method includes recommending a composition, a pose and a motion which are matched to the recognized subject and the background with reference to pre-recorded information about the composition, the pose and the motion.

Abstract: The present invention provides a graphic motion generating method and apparatus for modeling hair into elastic curves that are inextensible while twisting and curling of hair can be expressed, for applying an adaptive different subdividing method to subdivide a single strand of hair into several segments such that detailed bending and curling of the strands of hair can be expressed in the vicinities of roots and ends of the strands of hair, for modeling the respective segments of respective strands of hair into low degree-of-freedom elastic curves with degrees of freedom less than two such that geometric and dynamic physical quantities can be calculated in a short time, and for automatically generating a curvature vector of the elastic curve model from an initial hair curve by using a minimizing technique.

Abstract: A remote shading-based three-dimensional (3D) streaming apparatus includes a 3D streaming server and a 3D streaming client. The 3D streaming server includes a 3D primitive extraction unit for extracting 3D primitives from 3D scene data provided thereto; a 2D primitive conversion unit for converting the extracted 3D primitives into 2D primitives; a 2D scene and network packet construction unit for constructing 2D scene data and network packets; a network packet transmission unit for transmitting the network packets to a 3D streaming client. The 3D streaming client includes a 2D scene reconstruction unit for reconstructing 2D scene data from the network packets; a 2D primitive extraction unit for extracting 2D primitives from the 2D scene data; a 2D rasterizing unit for determining screen pixel values within a primitive region; and a display unit for providing 3D and/or virtual reality contents using the determined screen pixel value.

Abstract: Provided is an image-based volume data carving method for rapidly carving a specific area of dimensional volume data based on images. The method includes the steps of: generating a mask image to be carved from an input image; dividing a viewing transform matrix of the mask image into a shear transform matrix and a warp transform matrix, and calculating a scale factor from the shear transform matrix; modifying the mask image to be parallel to an axis of the volume data; shearing a volume slice in such a manner that the volume data can be parallel to viewing rays passing through a volume, and scaling the size of the volume slice; and carving part of the volume slice through an operation between the mask image and each volume slice.

Abstract: Provided is an apparatus for reconstructing a 3D shape of an object by using Helmholtz stereopsis. The apparatus includes: an image capturer for capturing two pairs of images satisfying Helmholtz reciprocity condition; a preprocessor for estimating optical and geometrical characteristics of a camera used for the image capturing; and a geometrical data reconstructor for converting Helmholtz restrictions generated from the respective pairs of the images into partial differential equations on the basis of the estimated optical and geometrical characteristics, and reconstructing 3D surface data of an object with depth discontinuity at a boundary between regions on the basis of the partial differential equations.

Abstract: Provided is an apparatus and method for determining stereo disparity based on two-path dynamic programming and GGCP. The apparatus includes a pre-processing unit for analyzing texture distribution of an input image by using a Laplacian of Gaussian (LOG) filter and dividing the input image into a homogeneous region and a non-homogeneous region; a local matching unit for determining candidate disparities to be included in an each pixel of all pixels; a local post-processing unit for removing candidate disparities in a pixel of low reliability by performing a visibility test betweens candidate disparities in each pixel to improve the reliability of the candidate disparity; and a global optimizing unit for determining a final disparity for candidate disparities in an each pixel by performing a dynamic programming.

Abstract: A locomotion generation method for a digital creature includes: imaging and capturing movements of a creature placed on a base plate having a printed pattern; extracting body position information, body posture information, leg posture information, and footprint information of the creature by analyzing captured images; and generating creature movement by applying inverse kinematics to the body position information, the body posture information, the leg posture information, and the footprint information of the creature.

Abstract: A method for calibrating a camera including (a) obtaining a two-dimensional (2D) homography that maps each of parallelograms projected onto images taken by two arbitrary cameras into a rectangle, wherein the 2D homography is defined as a rectification homography and wherein new cameras that have virtual images are defined as rectified cameras and a new infinite homography is generated between the two rectified cameras, the virtual images being transformed from original images by the rectification homography; (b) obtaining an original infinite homography by using the correlations among the new infinite homography, the rectification homography and the original infinite homography; and (c) obtaining intrinsic camera parameters based on the correlation between the original infinite homography and the intrinsic camera parameters, thereby calibrating the camera.

Abstract: A method of producing a locomotion animation includes calculating movement information of the objects on the basis of surrounding information of the objects and motion capture data for the subjects, and measuring a collision between the objects or between an object and an obstacle on the basis of the movement information to calculate riding motion information for the subjects. The movement information and the riding motion information are then synthesized to determine movement motion and riding animations of the objects. Therefore, the motions of locomotion can be naturally connected with each other.

Abstract: A method for texturing of 3D model in 2D environment includes (a) generating a texture map set for 3D model data; (b) UV unwrapping the 3D model data on each of projected planes to obtain a UV map set for each projected plane; (c) performing a 2D image authoring on the UV map set for each projected plane to produce an edited image; and (d) mapping the texture map set and the UV map set by reflecting the edited image to the texture map set and the UV map sets that are generated previously until a desired texture map set is completed.

Abstract: A method for transferring a pose from an original digital character to a newly-created digital character, includes: deriving constraints from a pose of the original character; modeling pose characteristics of each joint of the newly-created character as a probability distribution function having an input variable of a rotation angle of corresponding joint; and modeling pose characteristics of all joints of the newly-created character as a joint probability distribution function having input variables of rotation angles of corresponding joints. The method further includes extracting, based on the joint probability distribution function, the rotation angles of all joints of the newly-created character to thereby create a pose of the newly-created character, the rotation angles satisfying the constraints.

Abstract: Provided is a method for generating a three-dimensional (3D) mesh based on unorganized sparse 3D points to generate a mesh model that displays a 3D surface by using unorganized sparse 3D points extracted from a plurality of two-dimensional image. The 3D mesh generating method based on unorganized sparse 3D points includes the steps of: receiving a plurality of unorganized sparse 3D points, a plurality of two-dimensional (2D) corresponding point information, and images; generating an initial mesh by using the received 2D corresponding information; removing an abnormal face from the initial mesh; checking if unused 2D corresponding point information exists among the received 2D corresponding point information; if unused 2D corresponding point information exists, reorganizing the initial mesh by performing a constrained Delaunay triangulation; and if unused 2D corresponding point information does not exist in the result of the confirmation, generating a final mesh.

Abstract: A virtual reality embodying system uses 2D images and HDRI data taken of a target object through a camera to embody virtual reality. A modeling unit compares the 2D image's coordinate with a real coordinate to calculate a transform matrix, calculates a vanishing point of a reference vector, uses the vanishing point to calculate a camera matrix, uses the camera matrix and the transform matrix to calculate a rotation matrix and a translation matrix, and uses the rotation matrix and the translation matrix to model the 2D image into a virtual model. A rendering unit uses the HDRI data as texture to render the virtual model, and embodies the HDRI into an extended VRML node to apply the virtual model to the VRML environment.

Abstract: Provided is a method for generating a three-dimensional (3D) mesh based on unorganized sparse 3D points to generate a mesh model that displays a 3D surface by using unorganized sparse 3D points extracted from a plurality of two-dimensional image. The 3D mesh generating method based on unorganized sparse 3D points includes the steps of: receiving a plurality of unorganized sparse 3D points, a plurality of two-dimensional (2D) corresponding point information, and images; generating an initial mesh by using the received 2D corresponding information; removing an abnormal face from the initial mesh; checking if unused 2D corresponding point information exists among the received 2D corresponding point information; if unused 2D corresponding point information exists, reorganizing the initial mesh by performing a constrained Delaunay triangulation; and if unused 2D corresponding point information does not exist in the result of the confirmation, generating a final mesh.

Abstract: Provided is an image-based volume data carving method for rapidly carving a specific area of dimensional volume data based on images. The method includes the steps of: generating a mask image to be carved from an input image; dividing a viewing transform matrix of the mask image into a shear transform matrix and a warp transform matrix, and calculating a scale factor from the shear transform matrix; modifying the mask image to be parallel to an axis of the volume data; shearing a volume slice in such a manner that the volume data can be parallel to viewing rays passing through a volume, and scaling the size of the volume slice; and carving part of the volume slice through an operation between the mask image and each volume slice.

Abstract: A rendering apparatus for real-time global illumination and a method thereof are disclosed. The rendering apparatus includes: a spherical harmonic processor for creating light samples and creating spherical harmonics basis functions; a light model processor for transforming radiance of a HDRI image to spherical harmonics light coefficients using the spherical harmonic basis functions; a radiance transfer processor for previously calculating coefficients of a visibility and a geometric term for a global illumination model using the spherical harmonic basis function; a BRDF processor for generating a database of BRDF data and calculating coefficients of the BRDF data through smoothing; and a render unit for rendering the spherical harmonic light coefficients, the coefficients for the visibility and the geometric term, and the BRDF data coefficient using a rendering equation expressed as a dot product of a vector.

Abstract: Provided is an apparatus for reconstructing a 3D shape of an object by using Helmholtz stereopsis. The apparatus includes: an image capturer for capturing two pairs of images satisfying Helmholtz reciprocity condition; a preprocessor for estimating optical and geometrical characteristics of a camera used for the image capturing; and a geometrical data reconstructor for converting Helmholtz restrictions generated from the respective pairs of the images into partial differential equations on the basis of the estimated optical and geometrical characteristics, and reconstructing 3D surface data of an object with depth discontinuity at a boundary between regions on the basis of the partial differential equations.

Abstract: Provided is an apparatus and method for determining stereo disparity based on two-path dynamic programming and GGCP. The apparatus includes a pre-processing unit for analyzing texture distribution of an input image by using a Laplacian of Gaussian (LOG) filter and dividing the input image into a homogeneous region and a non-homogeneous region; a local matching unit for determining candidate disparities to be included in an each pixel of all pixels; a local post-processing unit for removing candidate disparities in a pixel of low reliability by performing a visibility test betweens candidate disparities in each pixel to improve the reliability of the candidate disparity; and a global optimizing unit for determining a final disparity for candidate disparities in an each pixel by performing a dynamic programming.