Abstract: A method of modeling a structure of a coronary artery of a subject may include: forming a learning-based shape model of the structure of the artery, based on positions of landmarks acquired from three-dimensional images; receiving a target image; and/or modeling the artery structure included in the target image, using the model. An apparatus for modeling a structure of a coronary artery may include: a memory configured to store a learning-based shape model of the artery, the learning-based shape model being formed based on positions of a plurality of landmarks acquired from three-dimensional images, the plurality of the landmarks corresponding to the artery; a communication circuit configured to receive a target image; and/or a processing circuit configured to model the artery structure included in the target image, using the model.

Abstract: A method for generating a three-dimensional (3D) image may detect a current eye position of a user and render a 3D image based on at least one of a previously detected eye position of the user and previously generated stereo images. A cycle at which the current eye position of user is detected and a cycle at which a 3D image is rendered may be asynchronous.

Abstract: A computing apparatus for providing a three-dimensional (3D) interactive user experience (UX) is provided. The computing apparatus may include an object position estimator configured to calculate first coordinates recognized by a user as a position of a first point of an object in a stereoscopic image. The computing apparatus may include a pointing determiner configured to determine whether the user points to the first point based on the first coordinates and second coordinates, the second coordinates representing a pointing position of the user.

Abstract: An eye tracking apparatus is operable in both first and second illumination environments where the second illumination is associated with a higher illumination environment than the first illumination. The apparatus includes an image capturer configured to capture an image of a user, an image processor configured to detect an eyepoint of the user in the captured image, and an optical source configured to emit infrared light to the user in a first illumination mode. The image capturer includes a dual bandpass filter configured to allow infrared light and visible light to pass.

Abstract: An image processing method includes tracking users viewing a three-dimensional (3D) image displayed on a screen, and generating a 3D image on the screen for each of a plurality of regions based on a result of the tracking, the plurality of regions being formed based on a number of the users is disclosed.

Abstract: An operating method of a display apparatus includes calculating a range of a movement of a user based on eye movement information indicating movements of eyes of the user; and adjusting a stereoscopic depth of a three-dimensional (3D) image based on the range of the movement.

Abstract: Creating a 3D face reconstruction model using a single 2D image and a generic facial depth map that provides depth information. In one example, the generic facial depth map is selected based on gender and ethnicity/race. In one embodiment, a set of facial features of the 2D image is mapped to create a facial-feature map, and a 2D mesh is created using the map. The same set of facial features is also mapped onto a generic facial depth map, and a 3D mesh is created therefrom. The 2D image is then warped by transposing depth information from the 3D mesh of the generic facial depth map onto the 2D mesh of the 2D image so as to create a reconstructed 3D model of the face. The reconstructed 3D model can be used, for example, to create one or more synthetic off-angle-pose images of the subject of the original 2D image.

Abstract: Creating a 3D face reconstruction model using a single 2D image and a generic facial depth map that provides depth information. In one example, the generic facial depth map is selected based on gender and ethnicity/race. In one embodiment, a set of facial features of the 2D image is mapped to create a facial-feature map, and a 2D mesh is created using the map. The same set of facial features is also mapped onto a generic facial depth map, and a 3D mesh is created therefrom. The 2D image is then warped by transposing depth information from the 3D mesh of the generic facial depth map onto the 2D mesh of the 2D image so as to create a reconstructed 3D model of the face. The reconstructed 3D model can be used, for example, to create one or more synthetic off-angle-pose images of the subject of the original 2D image.