Samsung Electronics Co., Ltd.

Seoul National University

Inha-Industry Partnership Institute

3Dis Co., Ltd.

In-Kyu Park

Mahn-jin Han

Alexander Olegovich Zhirkov

Alexey Victorovich Ignatenko

Sung-dae Cho

Sang-Uk Lee

Leonid Levkovich-Maslyuk

Man-Hee Lee

Mahn-Jin Han

Yun-Je Oh

Do-kyoon Kim

Min-Woo Lee

Tae-Hwa Hong

Heui-keun Choh

Chang-su Kim

Soo-Kyun Kim

Shin-jun Lee

Shin-Jun Lee

Duck-hoon Kim

Vladimir Vezhnevets

Anton Konouchine

Hui Zhang

Seok-Jin Won

Nitin Singhal

In-Wook Song

Leonid Ivanovich Leckovich-Maslyuk

Joo-yeon Han

Il-dong Yun

Leonid Ivanovich Levkovich-Maslyuk

Dmitri Alexandrovich Timasov

Yuri Matveevich Bayakovski

Il-Dong Yun

Mahn-Jin 307-602 Satbyeol Maeul Woobang Apt Han

Alexander Olegovich Room 16 Zhirkov

Provided are a method and apparatus for combining and composing a plurality of images into one image. An image processing unit calculates importance levels of the plurality of input images, respectively, according to selection criteria, selects at least two important images from among the plurality of input images according to the calculated importance levels, determines Regions Of Interest (ROIs) of the important images, selects the ROIs in one canvas, arranges corresponding important images at positions corresponding to the selected ROIs, and composes the arranged important images into one image.

Method and apparatus for composing image

Provided are a family of node structures, representing 3-dimensional objects using depth image, adoptable into MPEG-4 AFx for polygonal 3D representations. Family formats include DepthImage, PointTexture, and OctreeImage. DepthImage represents an object through union of its reference images and corresponding depth maps. PointTexture represents the object as a set of colored points parameterized by projection onto a 2D grid. OctreeImage converts same data into hierarchical octree-structured voxel model, set of compact reference images, and a tree of voxel-image correspondence indices. DepthImage and OctreeImage have animated versions, where reference images are replaced by videostreams. DIBR formats are convenient for 3D model construction from 3D range-scanning and multiple source video data. MPEG-4 framework allows construction of a variety of representations from the DIBR formats, providing flexible tools for effective 3D models work. DIBR format compression is achieved by application of image (video) compression techniques to depth maps and reference images (videostreams).

Apparatus and method for depth image-based representation of 3-dimensional object

A method for high-speed image processing based on graphic processing unit includes processing an input image for the image processing in a texture format of a 32 bit floating point, and performing a predetermined algorithm for the image processing on the input image through at least one or more Framebuffer Object (FOB) and outputting the result as texture data.

Method and apparatus for high-speed image processing based on graphic processing unit

A family of node structures for representing 3-dimensional objects using depth image are provided. These node structures can be adopted into MPEG-4 AFX for conventional polygonal 3D representations. Main formats of the family are DepthImage, PointTexture and OctreeImage. DepthImage represents an object by a union of its reference images and corresponding depth maps. PointTexture represents the object as a set of colored points parameterized by projection onto a regular 2D grid. OctreeImage converts the same data into hierarchical octree-structured voxel model, set of compact reference images and a tree of voxel-image correspondence indices. DepthImage and OctreeImage have animated versions, where reference images are replaced by videostreams. DIBR formats are very convenient for 3D model construction from 3D range-scanning and multiple source video data. MPEG-4 framework allows construction of a wide variety of representations from the main DIBR formats, providing flexible tools for effective work with 3D models. Compression of the DIBR formats is achieved by application of image (video) compression techniques to depth maps and reference images (videostreams).

A stereoscopic image display apparatus is provided which includes an image display panel and a parallax barrier having parallax barrier pieces in the front of the image display panel. In the stereoscopic image display apparatus, the image display panel has a pixel pattern in which left-eye sub pixels and right-eye sub pixels are alternately arranged in horizontal and vertical directions. The parallax barrier is spaced apart from the image display panel by a predetermined distance and the parallax barrier pieces with a predetermined size are arranged at a predetermined interval in the horizontal and vertical directions so as to allow a left eye and a right eye to separately recognize a left-eye image and a right-eye image formed by the left-eye sub pixels and the right-eye sub pixels, respectively. Accordingly, since a strip pattern is removed from s stereoscopic image, it is possible to obtain a natural stereoscopic image. In addition, since a strip pattern and a color mixing phenomenon are removed from s stereoscopic image, it is possible to obtain a natural and clear stereoscopic image.

Stereoscopic image display apparatus of net pattern

Node structure for representing 3-dimensional objects using depth image

A stereoscopic image display apparatus employing a front type parallax barrier is provided which can reduce a visible distance. The stereoscopic image display apparatus includes: a 2D image LCD panel having a first substrate in which a rear polarizing film is stacked on the rear surface thereof and a first switching element layer is stacked on the front surface thereof, a second substrate on which a color filter layer is stacked, and a first liquid crystal layer interposed between the first switching element layer and the color filter layer; a parallax barrier having a third substrate in which a front polarizing film is stacked on the front surface thereof and a transparent electrode layer is stacked on the rear surface thereof, a protective film, and a second liquid crystal layer interposed between the transparent electrode layer and the protective film; and an intermediate polarizing film interposed between the protective film of the parallax barrier and the second substrate of the 2D image LCD panel.

Stereoscopic image display apparatus

An apparatus and method for image-based 3D photorealistic head modeling are provided. The method for creating a 3D photorealistic head model includes: detecting frontal and profile features in input frontal and profile images; generating a 3D head model by fitting a 3D genetic model using the detected facial features; generating a realistic texture from the input frontal and profile images; and mapping the texture onto the 3D head model. In the apparatus and method, data obtained using a relatively cheap device, such as a digital camera, can be processed in an automated manner, and satisfactory results can be obtained even from imperfect input data. In other words, facial features can be extracted in an automated manner, and a robust 'human-quality' face analysis algorithm is used.

Method and apparatus for image-based photorealistic 3D face modeling

A method and apparatus removing redundant data of a simple texture model, using an extended depth image, and an image-based editing method and apparatus. The method involves calculating normal vectors of pixels projected into a three-dimensional (3D) space by using depth images among a plurality of simple texture images, the plurality of simple texture images rendering different aspects of a 3D model; calculating reliabilities of the pixels of each of the simple texture images by using the calculated normal vectors; and comparing the reliabilities of the pixels that originate from different simple texture images but render the same portion of the 3D model and removing the pixels having low reliabilities from the different simple texture images from which they respectively originate.

Image-based rendering and editing method and apparatus

Provided are methods and apparatuses for encoding and decoding three-dimensional object data, which consists of point texture data, voxel data, or octree data. The method of encoding three-dimensional object data involves generating three-dimensional object data having a tree structure in which nodes are attached labels indicating their types; encoding nodes of the three-dimensional object data; and generating the three-dimensional object data whose nodes are encoded into a bitstream. The apparatus for encoding three-dimensional object data includes a tree structure generator which generates three-dimensional object data having a tree structure in which nodes are attached labels indicating their types; a merging order selector which merges the nodes of the three-dimensional object data by referring to their labels; a node encoder which encodes merged nodes; and a bitstream generator which generates the three-dimensional object data whose merged nodes are encoded into a bitstream. The method of decoding three-dimensional object data involves reading-continue flag information from a bitstream of encoded three-dimensional object data and decoding the continue flag information; decoding note type information of the bitstream; decoding an 'S' node if the note type information indicates that a current node is an 'S' node and decoding a PPM node if the note type information indicates that the current node is a PPM node; and restoring the three-dimensional object data whose nodes are encoded to a tree structure. The apparatus for decoding three-dimensional object data includes a bitstream reader which receives a bitstream of encoded three-dimensional object data; a node decoder which decodes the bitstream; and a tree structure restorer which restores decoded nodes to a tree structure.

Method and apparatus for encoding and decoding three-dimensional object data

A method of perceptual 3-dimensional (3D) shape description and a method and apparatus for searching a perceptual 3D graphics model database established using the description method are provided. The description method includes: generating nodes that respectively correspond to parts of a part-based representation of a 3D shape model, the nodes including unary attributes of the parts; generating edges that include relational attributes between the nodes; and generating an attributed relational graph of the 3D shape model that is comprised of the nodes and the edges. The search method includes: receiving a predetermined 3D graphics model; transforming the received 3D graphics model into a perceptual 3D shape descriptor; and comparing the perceptual 3D shape descriptor with each of the perceptual 3D graphics models stored in the database to retrieve the 3D graphic models that are similar to the perceptual 3D shape descriptor. The searching apparatus includes: a query input unit that receives a query that is a 3D graphics model; a model/shape descriptor transforming unit that transforms the 3D graphic model received as the query into a perceptual 3D shape descriptor; a matching unit that compares the perceptual 3D shape descriptor with each of the perceptual 3D graphics models stored in the database to retrieve the models that are similar to the perceptual 3D shape descriptor; and a model output unit that outputs the retrieved model. A query by sketch or a query by editing is available, and the models that are similar to a query can be more accurately retrieved due to a double earth mover's distance method used to match query and model graphs.

Method of perceptual 3D shape description and method and apparatus for searching 3D graphics model database using the description method

Growing community of inventors

Seoul, South Korea

In-Kyu Park