Abstract: A device including a processor configured to generate, for each of plural query inputs, point information using factors individually extracted from a plurality of pieces of factor data for a corresponding query input and generate pixel information of a pixel position using the point information of points, the plural query inputs being of the points, in a 3D space, on a view direction from a viewpoint toward a pixel position of a two-dimensional (2D) scene.

Abstract: A method and apparatus with pose determination are provided. The method includes determining first pose information of a computing apparatus dependent on motion sensor information of motion of the computing apparatus, estimating second pose information of the computing apparatus dependent on feature point position information that is pre-defined for an object, and one or more feature points of the object that are extracted from an image captured by the computing apparatus, determining respective reliability values of the first pose information and the second pose information, and determining a pose of the computing apparatus for augmented reality (AR) content based on the first pose information, the second pose information, and the respective reliability values. AR content may be generated based on the determined pose.

Abstract: Disclosed are a method and device for representing rendered scenes. A data processing method of training a neural network model includes obtaining spatial information of sampling data, obtaining one or more volume-rendering parameters by inputting the spatial information of the sampling data to the neural network model, obtaining a regularization term based on a distribution of the volume-rendering parameters, performing volume rendering based on the volume-rendering parameters, and training the neural network model to minimize a loss function determined based on the regularization term and based on a difference between a ground truth image and an image that is estimated according to the volume rendering.

Abstract: A simultaneous localization and mapping-based electronic device includes: a data acquisition device configured to acquire external data; a memory; and a processor configured to be operatively connected to the data acquisition device and the memory, wherein the processor is further configured to extract features of surrounding objects from the acquired external data, calculate a score of a registration error of the extracted features when the number of the extracted features is greater than a set number stored in the memory, and select the set number of features from the among the extracted features, based on the calculated score.

Abstract: A method of estimating a position includes: determining a first rotation reference point based on localization information estimated for a target and map data; estimating a second rotation reference point from image data associated with a front view of the target; and correcting the localization information using a rotation parameter calculated based on the first rotation reference point and the second rotation reference point.

Abstract: A sensing data processing device is provided. The sensing data processing device may track keypoints within a full observable range of the sensing data processing device based on sensing data collected from a previous frame and a sensing data collected from a current frame through a reference sensor, the full observable range determined based on a combined field of view (FOV) of sensors, manage a new keypoint together with the keypoints in response to the new keypoint being detected, and perform localization of the device based on the managed keypoints.

Abstract: An electronic device includes a memory storing a plurality of motion prediction models, and a processor configured to estimate a current pose of the electronic device based on external data; predict a first motion of the electronic device at a future first prediction time through a first model in which the plurality of motion prediction models are combined for the future first prediction time, and calculate a first pose of the electronic device at the first prediction time based on the current pose and the first motion; and predict a second motion of the electronic device at a future second prediction time through a second model in which the plurality of motion prediction models are combined for the future second prediction time, and calculate a second pose of the electronic device at the second prediction time based on the first pose and the second motion.

Abstract: Disclosed is a recognition and training method and apparatus. The apparatus may include a processor configured to input data to a neural network, determine corresponding to a multiclass output a mapping function of a first class and a mapping function of a second class, acquire a result of a loss function including a first probability component that changes correspondingly to a function value of the mapping function of the first class and a second probability component that changes contrastingly to a function value of the mapping function of the second class, determine a gradient of loss corresponding to the input data based on the result of the loss function, update a parameter of the neural network based on the determined gradient of loss for generating a trained neural network based on the updated parameter. The apparatus may input other data to the trained neural network, and indicate a recognition result.

Abstract: A simultaneous localization and mapping-based electronic device includes: a data acquisition device configured to acquire external data; a memory; and a processor configured to be operatively connected to the data acquisition device and the memory, wherein the processor is further configured to extract features of surrounding objects from the acquired external data, calculate a score of a registration error of the extracted features when the number of the extracted features is greater than a set number stored in the memory, and select the set number of features from the among the extracted features, based on the calculated score.

Abstract: An apparatus for estimating an uncertainty includes a processor configured to receive a first tracking coordinate corresponding to a reference coordinate, the reference coordinate being included in first image data acquired by a camera sensor, image data acquired after the first image data; acquire, based on motion data acquired from a motion sensor and a depth value of the first image data, a second tracking coordinate corresponding to the reference coordinate, the second tracking coordinate including a motion-based tracking coordinate in the second image data; calculate a target coordinate distribution in the second image data based on the first tracking coordinate and the second tracking coordinate; acquire an estimated target coordinate and an uncertainty of the estimated target coordinate based on the calculated target coordinate distribution; and update the first tracking coordinate based on the estimated target coordinate.

Abstract: A processor-implemented method with pose estimation includes: tracking a position of a feature point extracted from image information comprising a plurality of image frames, the image information being received from an image sensor; predicting a current state variable of an estimation model for determining a pose of an electronic device, based on motion information received from a motion sensor; determining noise due to an uncertainty of the estimation model based on a residual between a first position of the feature point extracted from the image frames and a second position of the feature point predicted based on the current state variable; updating the current state variable based on the current state variable, the tracked position of the feature point, and the noise; and determining the pose of the electronic device based on the updated current state variable.

Abstract: A method of estimating a position of an image display device, the method including determining position information of a neck of a user based on position information of an image display device worn by the user, filtering the position information of the neck, and estimating a position of the image display device based on the filtered position information of the neck.

Abstract: Disclosed is a recognition and training method and apparatus. The apparatus may include a processor configured to input data to a neural network, determine corresponding to a multiclass output a mapping function of a first class and a mapping function of a second class, acquire a result of a loss function including a first probability component that changes correspondingly to a function value of the mapping function of the first class and a second probability component that changes contrastingly to a function value of the mapping function of the second class, determine a gradient of loss corresponding to the input data based on the result of the loss function, update a parameter of the neural network based on the determined gradient of loss for generating a trained neural network based on the updated parameter. The apparatus may input other data to the trained neural network, and indicate a recognition result.

Abstract: A method and apparatus with pose determination are provided. The method includes determining first pose information of a computing apparatus dependent on motion sensor information of motion of the computing apparatus, estimating second pose information of the computing apparatus dependent on feature point position information that is pre-defined for an object, and one or more feature points of the object that are extracted from an image captured by the computing apparatus, determining respective reliability values of the first pose information and the second pose information, and determining a pose of the computing apparatus for augmented reality (AR) content based on the first pose information, the second pose information, and the respective reliability values. AR content may be generated based on the determined pose.

Abstract: A modeling method searches for a sequence matched to a user input using a fluid animation graph generated based on similarities among frames included in sequences included in the fluid animation graph and models a movement corresponding to the user input based on a result of the searching. Provided also is a corresponding apparatus and a method for preprocessing for such modeling.

Abstract: A processor-implemented pose prediction method includes: estimating a pose of a user for a predetermined period of time in real time; calculating an estimation confidence of the estimated pose; determining a weight for the pose of the user based on the estimated pose and the estimation confidence; and predicting a pose of the user after the predetermined period of time, based on the weight.

Abstract: A processor implemented method includes: calculating edge direction information of edge component pixels extracted from an input image; determining an inlier pixel among the edge component pixels based on the edge direction information and virtual horizontal line information; estimating a rotation reference point based on the inlier pixel; and correcting localization information of the apparatus based on the estimated rotation reference point.

Abstract: A method of estimating a position of an image display device, the method including determining position information of a neck of a user based on position information of an image display device worn by the user, filtering the position information of the neck, and estimating a position of the image display device based on the filtered position information of the neck.

Abstract: Provided is a method for simultaneous localization and mapping (SLAM), the method including obtaining a current frame image input through a camera, performing scene recognition on the current frame image to obtain a key frame image having a greatest similarity to the current frame image in a global map, and obtaining a camera pose of the current frame image based on the key frame image.

Abstract: Localization apparatuses and methods are disclosed where a localization apparatus extracts a feature of an object from an input image, generates an image in which the object is projected with respect to localization information of a device based on map data, and evaluates the localization information based on feature values corresponding to vertices included in a projection image.