Abstract: A method and an apparatus search an image using a feature point. The image search method extracts at least one feature point from an image and describes the extracted at least one feature point in stages, thereby generating a hierarchical feature point descriptor. In addition, the method may search for information matching the feature point descriptor from a local database (DB) included in a terminal or a remote DB included in a server.

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: 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.

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: An apparatus and corresponding method are provided to match images and include assigning depth candidate values to a pixel in a first image, and reassigning third depth candidate values to a first pixel in the first image based on first depth candidate values assigned to the first pixel and second depth candidate values assigned to a second pixel adjacent to the first pixel. The apparatus and method also include determining one of the third depth candidate values to be a depth value of the first pixel, and matching the first pixel and a third pixel in a second image corresponding to the determined depth value of the first pixel.

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: Provided is a camera pose estimation apparatus that estimates an initial camera pose using one of an input depth image and an input color image, and refines the initial camera pose using the other image. When the initial camera pose is estimated using the input depth image, the radius of a first area, in which color information is matched for refinement, can be adaptively set according to the distribution of the depth value of at least one first point that is subject to matching.

Abstract: A method and an apparatus for registering a face, and a method and an apparatus for recognizing a face are disclosed, in which a face registering apparatus may change a stored three-dimensional (3D) facial model to an individualized 3D facial model based on facial landmarks extracted from two-dimensional (2D) face images, match the individualized 3D facial model to a current 2D face image of the 2D face images, and extract an image feature of the current 2D face image from regions in the current 2D face image to which 3D feature points of the individualized 3D facial model are projected, and a face recognizing apparatus may perform facial recognition based on image features of the 2D face images extracted by the face registering apparatus.

Abstract: A method of generating a three-dimensional (3D) face model includes extracting feature points of a face from input images comprising a first face image and a second face image; deforming a generic 3D face model to a personalized 3D face model based on the feature points; projecting the personalized 3D face model to each of the first face image and the second face image; and refining the personalized 3D face model based on a difference in texture patterns between the first face image to which the personalized 3D face model is projected and the second face image to which the personalized 3D face model is projected.

Abstract: Provided is a camera motion estimation method and apparatus that may estimate a motion of a depth camera in real time. The camera motion estimation apparatus may extract an intersection point from plane information of a depth image, calculate a feature point associated with each of planes included in the plane information using the extracted intersection point, and extract a motion of a depth camera providing the depth image using the feature point. Accordingly, in an environment where an illumination environment dynamically varies, or regardless of a texture state within a space, the camera motion estimation apparatus may estimate a camera motion.

Abstract: At least one example embodiment discloses a facial recognition apparatus configured to obtain a two-dimensional (2D) input image including a face region of a user, detect a facial feature point from the 2D input image, adjust a pose of a stored three-dimensional (3D) facial model based on the detected facial feature point, generate a 2D projection image from the adjusted 3D facial model, perform facial recognition based on the face region in the 2D input image and a face region in the 2D projection image, and output a result of the facial recognition.

Abstract: Provided is an image processing apparatus for extracting a three-dimensional (3D) feature point from a depth image. An input processing unit may receive a depth image and may receive, via a user interface, selection information of at least one region that is selected as a target region in the depth image. A geometry information analyzer of the image processing apparatus may analyze geometry information of the target region within the input depth image, and a feature point extractor may extract at least one feature point from the target region based on the geometry information of the target region.

Abstract: An apparatus for estimating a camera pose includes an image acquisition unit to acquire a photographed image, a motion sensor to acquire motion information of the apparatus for estimating the camera pose, a static area detector to detect a static area of the photographed image based on the photographed image and the motion information, and a pose estimator to estimate a camera pose based on the detected static area.

Abstract: A method and an apparatus search an image using a feature point. The image search method extracts at least one feature point from an image and describes the extracted at least one feature point in stages, thereby generating a hierarchical feature point descriptor. In addition, the method may search for information matching the feature point descriptor from a local database (DB) included in a terminal or a remote DB included in a server.

Abstract: Provided are an electronic device including a transparent display and a method of controlling the electronic device, the method including acquiring a first image based on an optical display mode in which light incident from an object is transmitted; acquiring a second image based on a video display mode in which an image captured from the object is displayed; and displaying the first image and the second image on the transparent display by mixing the first image and the second image.

Abstract: A method and apparatus for detecting a three-dimensional (3D) point cloud point of interest (POI), the apparatus comprising a 3D point cloud data acquirer to acquire 3D point cloud data, a shape descriptor to generate a shape description vector describing a shape of a surface in which a pixel point of a 3D point cloud and a neighboring point of the pixel point are located, and a POI extractor to extract a POI based on the shape description vector is disclosed.

Abstract: A multi-layered augmented reality system and method may extract a target object and a background from an image frame, may track the target object and the background, may apply different coordinate systems to a first virtual object corresponding to the target object and a second virtual object corresponding to the background, and may independently control the first virtual object and the second virtual object.

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 method and an apparatus search an image using a feature point. The image search method extracts at least one feature point from an image and describes the extracted at least one feature point in stages, thereby generating a hierarchical feature point descriptor. In addition, the method may search for information matching the feature point descriptor from a local database (DB) included in a terminal or a remote DB included in a server.

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.