Abstract: An image processing apparatus is provided. The image processing apparatus includes a light capturing unit to generate light environment information by photographing a light environment of an object, and an object capturing unit to generate object information by photographing the object. The image processing apparatus may further include a modeling unit to generate a 3-dimensional (3D) model by reflecting the light environment information and the object information, and a rendering unit to render a resultant image with respect to at least one view using the 3D model.

Abstract: A data processing apparatus and method. A vertex grouping unit of the data processing apparatus may group, into at least one group, a plurality of vertices included in a three-dimensional (3D) object desired to be compressed. A prediction mode determination unit may determine a prediction mode for compressing a vertex position with respect to each of the at least one group. A coder may code a prediction error vector and an identification (ID) index of the prediction mode determined with respect to each of the at least one group.

Abstract: Provided is an apparatus and method to create a model of a target organ of a patient. The apparatus and method generate a deformation matrix between at least two shape models of a target organ based on at least two three-dimensional (3D) images of the target organ. The apparatus and method also extract constraints about the target organ from a two-dimensional (2D) image of the target organ. The apparatus and method create the model of the target organ based on the constraints and the deformation matrix.

Abstract: A marker-less augmented reality system that may extract a plurality of planes included in an image generated by a camera, based on three-dimensional (3D) information of the image, and may estimating a pose of the camera based on a correspondence among the plurality of planes extracted, and an operating method thereof.

Abstract: An image processor, a lighting processor, and a method therefore are provided. According to one aspect of the invention, the lighting processor can extract information related to defuse lighting applied to a real object using a colored image and a depth image of the real object. The lighting processor can recover the diffuse image for the real object using the extracted information related to diffuse lighting, and generate either a speculum image or a shadow image using the recovered diffuse image and the colored image.

Abstract: A method of generating elasticity data, an elasticity generating apparatus, and an elasticity image generating system based thereon is provided. The method of generating elasticity data includes receiving first elasticity data of a region of interest (ROI) in a subject, the first elasticity data indicating elasticity corresponding to a predetermined degree of deformation, receiving second elasticity data of a local region of the ROI in the subject, the second elasticity data indicating elasticity corresponding to a local degree of deformation that is greater than the predetermined degree of deformation, and generating third elasticity data of the ROI in the subject based on the received first elasticity data and second elasticity data, the third elasticity data indicating elasticity corresponding to a global degree of deformation that is greater than the predetermined degree of deformation.

Abstract: Provided is an apparatus and method of multi-view rendering. A method of multi-view rendering includes rendering one or more 3D objects based on a first viewpoint, transforming pixel values of pixels of the first viewpoint, which are obtained by the rendering of the 3D objects, into pixel values of pixels based on a second viewpoint that is different from the first viewpoint, detecting an occlusion region that is a remaining region other than a region represented by the pixel values obtained by the transforming of the pixel values in an image based on the second viewpoint, and rendering the detected occlusion region based on the second viewpoint.

Abstract: An image processing apparatus. The image processing apparatus may perform filtering to emphasize a surface lighting of a low frequency band from an input lighting environment image, and may also perform at least one virtual point light (VPL) sampling from the input lighting environment image. The image processing apparatus may perform precomputed radiance transfer (PRT) based rendering using the filtered lighting environment image and VPL based rendering using the sampled VPL.

Abstract: A method and apparatus for expressing a rigid area based on expression control points that express a motion change of the rigid area with respect to an input expression. The method and apparatus express the rigid area by interpolating a change of expression of an avatar using a weight applied to an expression vector related to a plurality of expression samples to express the input expression and also using a transformation matrix set corresponding to the rigid area of each of the plurality of expression samples.

Abstract: Image processing apparatus and method. A modeling unit may generate a three-dimensional (3D) model corresponding to an actual object from an input color image and an input depth image corresponding to the input color image. A calculator may perform photon-based rendering with respect to an input virtual object and the 3D model based on input light environment information, and may generate a difference image comprising color distortion information occurring by inserting the virtual object into the 3D model. A rendering unit may generate a result image comprising the virtual object by synthesizing the difference image and the input color image.

Abstract: Provided is an image processing apparatus. The image processing apparatus may adaptively sample a virtual point light (VPL) at a light view within a three-dimensional (3D) model. The image processing apparatus may adaptively sample a surface point at a camera view.

Abstract: A method and apparatus for realistically expressing teeth performs rendering on a shape model of the teeth using a hybrid normal map based on materials and characteristics of the teeth in order to more realistically express the teeth.

Abstract: A graphic processing unit (GPU) and method for decompressing compressed 3-dimensional (3D) compressed data. The GPU may extract segment information by analyzing a compressed data header and decompress segments included in a bit stream based on the segment information.

Abstract: An apparatus and method for encoding a 3D mesh, and an apparatus and method for decoding the 3D mesh are disclosed. The 3D mesh encoding apparatus may determine mesh information including position information of each of vertices constituting the 3D mesh, and connectivity information among the vertices, based on a level, and may progressively encode the determined mesh information based on the level, thereby reducing an error with an original 3D object when compared to an equal transmission rating.

Abstract: Provided is a method and apparatus for realistically reproducing an eyeball that may verify and analyze a material property and a deformation property with respect to each of constituent portions of an eyeball and may render each of the constituent portions based on the analyzed priorities, thereby more realistically reproducing the eyeball.

Abstract: A data processing apparatus and method. A vertex grouping unit of the data processing apparatus may group, into at least one group, a plurality of vertices included in a three-dimensional (3D) object desired to be compressed. A prediction mode determination unit may determine a prediction mode for compressing a vertex position with respect to each of the at least one group. A coder may code a prediction error vector and an identification (ID) index of the prediction mode determined with respect to each of the at least one group.

Abstract: Provided is a realistic pose generating apparatus that may render an input pose by deforming a basic shape to a shape of the input pose based on a displacement value of a shape corresponding to a difference between a shape interpolation function with respect to the input pose and the shape interpolation function with respect to each of major poses, and by deforming a basic texture to a texture of the input pose based on a displacement value of a texture corresponding to a difference between a texture interpolation function with respect to the input pose and the texture interpolation function with respect to each of the major poses.

Abstract: Provided are a three-dimensional (3D) object transformation apparatus and a method using the same, that may transform the 3D object to obtain animation effects. When transforming the 3D object, coordinates of a vertex constituting the 3D object may be controlled to naturally transform the 3D object.

Abstract: A rendering system and method, and a recording medium therefor are provided. The rendering system imports geometry and hierarchy structure information on a three-dimensional (3D) computer-aided design (CAD) model, which is produced in a commercial 3D CAD system, from the 3D CAD system through an interface, performs scene editing necessary for rendering without changing the initially modeled data, and then performs rendering. Accordingly, it is not necessary to correct the geometry data and restore the hierarchy structure information, and rendering can be easily performed in a short time.

Abstract: A rendering system and method, and a recording medium therefor are provided. The rendering system imports geometry and hierarchy structure information on a three-dimensional (3D) computer-aided design (CAD) model, which is produced in a commercial 3D CAD system, from the 3D CAD system through an interface, performs scene editing necessary for rendering without changing the initially modeled data, and then performs rendering. Accordingly, it is not necessary to correct the geometry data and restore the hierarchy structure information, and rendering can be easily performed in a short time.