Abstract: A method of controlling a display device includes rendering a plurality of viewpoint images, generating a plurality of sub-images based on the plurality of viewpoint images and a plurality of mapping pattern images corresponding to the plurality of viewpoint images, generating a single light-field image based on the plurality of sub-images, and outputting the single light-field image.

Abstract: An apparatus for estimating a camera pose according to an embodiment of the present disclosure includes a similar image searcher, a clusterer, and an estimator. The similar image searcher searches for a plurality of images similar to an input image, from among a plurality of previously-stored images, based on the input image. The clusterer creates a cluster including at least some similar images meeting predetermined conditions, from among the plurality of similar images, based on viewpoint data tagged to each of the plurality of similar images. The estimator estimates a pose of a camera that has generated the input image, based on the cluster.

Abstract: A system for rendering 6 degree-of-freedom virtual reality according to an embodiment of the present disclosure includes a visibility test module performing a visibility test for determining whether a current point of interest where a main viewpoint is directed is visible for each of a plurality of reference viewpoints and generating visibility information by identifying the number of invisible fragments of each reference viewpoint according to the performance result, a reference viewpoint selection module selecting a final reference viewpoint for a rendering process for a current frame based on the visibility information for each of the plurality of reference viewpoints and a preset selection criterion, and a rendering process module performing an image-based rendering process by using a color image and a depth image corresponding to the final reference viewpoint.

Abstract: A point cloud information generation apparatus according to an embodiment includes a 360-degree image acquirer configured to acquire a 360-degree image of a three-dimensional (3D) space, a point cloud information generator configured to generate first point cloud information for the 3D space from the 360-degree image, and a viewpoint orientation image generator configured to generate a plurality of viewpoint orientation images from the 360-degree image based on a reference viewpoint in the 360-degree image, wherein the point cloud information generator further configured to generate second point cloud information for the 3D space from the plurality of viewpoint orientation images.

Abstract: According to the disclosed embodiments, virtualized information of a three-dimensional position for a position selected by the user is provided so that the user can place virtual content at an accurate position when authoring AR content. According to an embodiment, an apparatus for generating point cloud data includes a hardware processor to implement a feature point extractor to extract feature points from images obtained by capturing a three-dimensional region, a point cloud data generator to generate point cloud data related to the three-dimensional region on the basis of the extracted feature points, an overlay image display to display the generated point cloud data by overlaying the point cloud data on a currently captured image, and a three-dimensional position determiner to determine a three-dimensional position for a position selected by a user in the image.

Abstract: Disclosed are a pictogram recognition apparatus, a pictogram recognition system, and a pictogram recognition method, wherein the pictogram recognition method includes acquiring learning data, acquiring an image including a pictogram, extracting at least one zone from the image, acquiring a descriptor corresponding to the at least one zone, recognizing a pictogram by comparing the descriptor with the learning data and providing a user with information corresponding to the recognized pictogram.

Abstract: An augmented reality-based video calling system includes a first terminal configured to capture a video and a second terminal configured to add virtual content to the video captured by the first terminal and provide information regarding the added virtual content to the first terminal. The first terminal calculates 3D position coordinates of the virtual content in a 3D space corresponding to the video on the basis of the provided information regarding the virtual content, combines the virtual content with the video using the calculated 3D position coordinates, and display the virtual content combined with the video.

Abstract: Disclosed are a pictogram recognition apparatus, a pictogram recognition system, and a pictogram recognition method, wherein the pictogram recognition method includes acquiring learning data, acquiring an image including a pictogram, extracting at least one zone from the image, acquiring a descriptor corresponding to the at least one zone, recognizing a pictogram by comparing the descriptor with the learning data and providing a user with information corresponding to the recognized pictogram.

Abstract: An augmented reality content display method and an apparatus and system for performing the same are disclosed. The method includes extracting, by a feature point classification device, feature points from a plurality of images captured while changing a capture point such that at least one of a capture position and a capture orientation is changed, tracking, by the feature point classification device, feature points extracted from the same area of the plurality of images to associate the tracked feature points with one another, calculating, by the feature point classification device, uncertainty about a position of the associated feature points, and classifying and storing, by the feature point classification device, the associated features as a recognition reference feature point group or a dummy feature point group according to the position uncertainty.

Abstract: Provided are an apparatus and method for tracking augmented reality content using a mobile sensor. The method includes recognizing an augmented reality marker from an input image and calculating a position and posture of the recognized augmented reality marker, calculating a position and posture of augmented reality content corresponding to the augmented reality marker using the calculated position and posture of the augmented reality marker, synthesizing the augmented reality content with the input image using the calculated position and posture of the augmented reality content, and displaying the synthesized image, updating the position and posture of the augmented reality content using a 6-axis sensor when the augmented reality marker is not recognized in the input image; and synthesizing the augmented reality content with the input image using the updated position and posture of the augmented reality content, and displaying the synthesized image.

Abstract: Provided are an apparatus and method for tracking augmented reality content using a mobile sensor. The method includes recognizing an augmented reality marker from an input image and calculating a position and posture of the recognized augmented reality marker, calculating a position and posture of augmented reality content corresponding to the augmented reality marker using the calculated position and posture of the augmented reality marker, synthesizing the augmented reality content with the input image using the calculated position and posture of the augmented reality content, and displaying the synthesized image, updating the position and posture of the augmented reality content using a 6-axis sensor when the augmented reality marker is not recognized in the input image; and synthesizing the augmented reality content with the input image using the updated position and posture of the augmented reality content, and displaying the synthesized image.