Samsung Electronics Co., Ltd.

Hui Zhang

Sangwook Lee

Jaejoon Han

Byung In Yoo

Do-kyoon Kim

Seok-yoon Jung

Youngsung Kim

Changkyu Choi

Keun-ho Kim

Vladimir Vezhnevets

Anton Konouchine

Heui-keun Choh

Shinjun Lee

Seokyoon Jung

In-Kyu Park

Duckhoon Kim

Ildong Yun

Sehyuk Yun

Tianchu Guo

Deheng Qian

Xiabing Liu

Seok-Yoon Jung

Keun-Ho Kim

Provided are an apparatus, method, and medium for generating a panoramic image. In the apparatus, a previously captured image and a currently captured image are projected onto a predetermined curved surface so as to form a first mapping image and a second mapping image, respectively. Movement values in predetermined directions are calculated for maximizing a color similarity between overlapped sections of the first and second mapping images. A panoramic image is generated using the first and second mapping images and the calculated movement values. Therefore, overlapped sections of neighboring images can be precisely superposed and aligned when a panoramic image is generated using a series of images.

Apparatus, method, and medium for generating panoramic image using a series of images captured in various directions

A modeling method, medium, and system. The modeling method may include specifying an object in a plurality of 2 dimensional (2D) images expressed from different view points, considering an edge and contents of each component of each 2D image, generating a 3 dimensional (3D) model of each specified object, and matching the generated 3D models considering relative locations of each generated 3D model. Accordingly, a realistic 3D model of an object expressed in an image can be accurately generated.

Method, medium, and system with 3 dimensional object modeling using multiple view points

A modeling method, medium, and system. The modeling method identifies a object within an image by detecting edges within the image, determines a complexity of the identified object based upon detected surface orientations of the identified object relative to a defined surface of the image, selectively, based upon the determined complexity, generates one or more surfaces for a 3D model by identifying one or more vanishing points for one or more corresponding surfaces, respectively, of the identified object and respectively analyzing the identified one or more vanishing points relative to respective determined points of the one or more corresponding surfaces of the image, and generates the 3D model by combining the one or more surfaces in a 3D space.

Method, medium, and system implementing 3D model generation based on 2D photographic images

Provided are an apparatus, method, and medium for processing an image. In the apparatus, at least one image selected from images to be stitched so as to make colors of overlapped sections of the images as identical with each other as possible and operating again in response to a re-alignment signal, and an image correction unit generating the re-alignment signal after correcting a color of at least a part of the overlapped sections as a result of the shifting of the at least one image in consideration of colors of the overlapped sections Then the shifting of the image is repeated. Therefore, even when the overlapped sections of the images are not identical in color, the overlapped sections of the images can be precisely aligned when the images are stitched for forming a panoramic image, thereby making the panoramic image more accurate.

An apparatus and method of producing a three-dimensional structural sketch (3DSS) and a computer-readable recording medium on which a computer program for executing the method is recorded are provided. The apparatus includes a property-detecting unit detecting a unary property of each part of a predetermined two-dimensional sketch and relational properties of the parts; a node-generating unit receiving the detected unary properties and the parts and converting the parts into nodes having three-dimensional shapes together with the detected unary properties; and a node-arranging unit receiving the detected relational properties and the nodes, arranging the nodes according to the detected relational properties, and generating a three-dimensional structural sketch, wherein the unary property includes geometric property and the relational property include topologic property. Thus, the apparatus can easily produce a 3DSS and update the produced 3DSS.

Apparatus and method of producing 3D structural sketch and computer-readable recording medium on which compute program for executing the method is recorded

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

Growing community of inventors

Yongin-si, South Korea

Hui Zhang