Abstract: A system for compressing a picture includes: an information extraction unit for extracting information needed for encoding during a picture scene composition and animation process using a modeling object; and a rendering unit for generating an uncompressed picture sequence by rendering the object where the picture scene composition and animation process is performed. Further, the system for compressing a picture includes an encoding unit for generating a compressed bit stream by encoding the picture sequence from the rendering unit based on the information extracted by the information extraction unit.

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 method for reconstructing a 3D shape model of an object by using multi-view image information, includes: inputting multi-view images obtained by photographing the object from multiple viewpoints in a voxel space, and extracting silhouette information and color information of the multi-view images; reconstructing visual hulls by silhouette intersection using the silhouette information; and approximating polygons of cross-sections of the visual hulls to a natural geometric shape of the object by using the color information. Further, the method includes expressing a 3D geometric shape of the object by connecting the approximated polygons to create a mesh structure; extracting color textures of a surface of the object by projecting meshes of the mesh structure to the multi-view image; and creating a 3D shape model by modeling natural shape information and surface color information of the object.

Abstract: A method for producing a 3D facial animation using a single facial video stream, includes producing a representative joint focused on a major expression producing element in a 3D standard facial model, producing a statistical feature-point model of various facial expressions of different people in the 3D standard facial model, moving each feature-point of the statistical feature-point model by tracking a change in facial expressions of the video stream, calculating a transformation coefficient of the representative joint corresponding to a variation of the feature-point of the 3D standard facial model, and producing a 3D facial animation by applying the calculated transformation coefficient to transform the representative joint.

Abstract: A multi-view camera color calibration method using a color checker chart, includes measuring a brightness range of photographic data being input from multiple cameras; photographing the color checker chart for each camera and adjusting a brightness value of the chart to be within the brightness range of an input image of each camera; correcting brightness of each camera by using a gray patch of the checker chart; modeling a relationship between a color value of the checker chart obtained by each camera and a standard color value provided by the color checker chart; and correcting differences in color as a result of the modeling, to calibrate colors among the multiple cameras. Therefore, the three-dimensional information of a moving object for photography which cannot be photographed by moving only one camera is capable of being restored.

Abstract: A method for creating a 3D face model by using multi-view image information, includes: creating a mesh structure for expressing an appearance of a 3D face model by using a first multi-view image obtained by capturing an expressionless face of a performer; and locating joints of a hierarchical structure in the mesh structure, by using a second multi-view image obtained by capturing an expression performance of the performer. Further, the method includes creating a 3D face model that is animated to enable reproduction of a natural expression of the performer, by setting dependency between the joints and the mesh structure.

Abstract: Disclosed is a technology for measuring a degree of accuracy of a 3D graphical model by using images. The technology includes creating camera parameters by calculating a position, a direction, and intrinsic parameters of a camera through a calibration of the camera to a reference image which is photographed for reference during creation of the 3D graphical model of an actually existing object; calculating a position and a direction of the 3D graphical model based on a corresponding relation between the reference image and 3D graphical model data obtained by digitizing the actually existing object; creating a synthesized image by rendering the 3D graphical model using the camera parameters; extracting characteristics of the reference image and the synthesized image; and calculating distance and length errors based on a corresponding relation between the extracted characteristics of the two images.

Abstract: A head motion tracking method for three-dimensional facial model animation, the head motion tracking method includes acquiring initial facial motion to be fit to an image of a three-dimensional model from an image inputted by a video camera; creating a silhouette of the three-dimensional model and projecting the silhouette; matching the silhouette created from the three-dimensional model with a silhouette acquired by a statistical feature point tracking scheme; and obtaining a motion parameter for the image of the three-dimensional model through motion correction using a texture to perform three-dimensional head motion tracking. In accordance with the present invention, natural three-dimensional facial model animation based on a real image acquired with a video camera can be performed automatically, thereby reducing time and cost.

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 are system and method for generating a 3D facial model and animation using one video camera. The system includes a pre-processing part, a facial model generating part, a transferring part, a projecting part, an error calculating part, and a mesh transforming part. The pre-processing part sets correspondence relations with other meshes, generates an average 3D facial model, and generates a geometrical model and a texture dispersion model. The facial model generating part projects the average 3D facial onto an expressionless facial image frame that stares a front side to generate a performer's 3D facial model. The transferring part transfers a 3D facial model template having an animation-controlled model to the performer's 3D facial model to generate the performer's 3D facial model. The projecting part projects the performer's 3D facial model onto a facial animation video frame including a facial expression. The error calculating part calculates an error projected by the projecting part.

Abstract: Provided is a camera self-calibration method that calculates a focal length of a fixed zoom lens camera from a correspondence point position between images. In the method, a cost function, which is a function of a focal length, is defined, and a focal length that minimizes the defined cost function is obtained to obtain a focal length that allows 3D recovery results of correspondence points calculated from all image pairs coincide with one another. Therefore, reliability of the calculated focal length can be easily verified, and the focal length of the camera can be stably calculated even when the position of input correspondence point is inaccurately given.

Abstract: A method for modeling a three dimensional shape of object using a level set solution on a partial differential equation derived from a Helmholtz reciprocity condition is provided. The method includes the steps of: a) inputting an image pair satisfying a Helmholtz reciprocity condition; b) performing an optical correction and simultaneously performing a geometric correction; c) performing a camera selection to select cameras capable of seeing a point (X, Y, Z), and defining and calculating a cost function by the Helmholtz reciprocity condition; d) calculating a speed function of a PDE that minimizes the cost function obtained in the step c); and e) generating a three dimension mesh model from a set of points configuring the object surface provided from the step d), and deciding a final three dimension mesh model by comparing cost function values.

Abstract: Provided is a method for creating a 3-D curved surface by using corresponding curves in a plurality of images. The method includes performing an NURBS fitting curve with respect to one image in a plurality of images having camera calibration and extracted camera parameter by using control points designated in a curve characterizing a subject shape. When the curve fitting is performed with respect to the curve that commonly exists in more than two images, a 3-D curve is created by using a camera calibration information, or a 3-D curved surface is created by creating a plurality of 3-D curves or straight lines. Therefore, a 3-D curved surface model can be easily and quickly created by simplifying a complex modeling process for an actual object modeling into an actual image-based modeling process.

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 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: In a virtual character control system, a character form mesh linked to articulation information of a character including articulations and at least one item mesh linked to the articulation information are stored in a set format. A temporary mesh generator selects an item mesh attached to the character from among the at least one item mesh according to item removal information, and combines the selected item mesh and the character form mesh to generate a temporary mesh. A character motion controller performs mesh skinning on the temporary mesh according to character motion control information to link the character form mesh and the item mesh to the character motion control information, thereby very effectively controlling motion of the virtual character.

Abstract: The present invention relates to a system and method for operation optimization in a hardware graphics accelerator for real-time rendering, which optimizes operation number or sequence in the hardware graphics accelerator so as to improve the display speed of three-dimensional objects on a computer screen when the three-dimensional objects are displayed with the hardware graphics accelerator.