Samsung Electronics Co., Ltd.

University of Southern California

Korea University Industrial Academic Collaboration Foundation

Korea University Industrial & Academic Collarbortion

Tae Hyun Rhee

Do Kyoon Kim

Seon Min Rhee

Min Su Ahn

Yong Beom Lee

In Woo Ha

Hyun Jung Shim

Chang Gyeom Kim

Abhijeet Ghosh

Dae Youn Lee

Jae Kyun Ahn

Jay Busch

Kyung Hwan Kim

Sang Wook Kim

Paul E Debevec

Na Hyup Kang

Jen-Yuan Chiang

Matt Chiang

Paul Devebec

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.

Apparatus and method for image processing

Disclosed is a method and apparatus for encoding a three-dimensional (3D) mesh. The method for encoding the 3D mesh includes determining a priority of a gate configuring a 3D mesh corresponding to a 3D object, removing vertices configuring the 3D mesh using the determined priority of the gate, and simplifying the 3D mesh.

Method and apparatus for encoding a 3D mesh

An image processing apparatus may include a light capturing unit to generate light environment information by photographing or capturing a light environment of an object, and an object capturing unit to generate object information by photographing or capturing the object. The image processing apparatus may further include a modeling unit to generate a 3-dimensional (3D) model by reflecting or combining 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.

Image processing apparatus and method

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.

Apparatus and method for encoding three-dimensional (3D) mesh, and apparatus and method for decoding 3D mesh

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.

Image processor, lighting processor and method therefor

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.

Method and apparatus for creating model of patient specified target organ

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.

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.

Method and apparatus for expressing rigid area based on expression control points

A plane detection apparatus for detecting at least one plane model from an input depth image. The plane detection apparatus may include an image divider to divide the input depth image into a plurality of patches, a plane model estimator to calculate one or more plane models with respect to the plurality of patches including a first patch and a second patch, and a patch merger to iteratively merge patches having a plane model a similarity greater than or equal to a first threshold by comparing plane models of the plurality of patches. When a patch having the plane model similarity greater than or equal to the first threshold is absent, the plane detection apparatus may determine at least one final plane model with respect to the input depth image using previously merged patches.

Apparatus and method for plane detection

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.

Method and apparatus for realistically reproducing eyeball

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.

Plane-characteristic-based markerless augmented reality system and method for operating same

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.

Graphic processing unit and method for decompressing data

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.

Apparatus and method for realistically expressing teeth

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.

Growing community of inventors

Yongin-si, South Korea

Tae Hyun Rhee