Abstract: A video encoder is provided. The video encoder according to an example embodiment includes: a differentiable prediction (DP) module configured to output an optimal initial search position by performing full search in a predetermined area by using a pair of frames of a video as input; and a motion estimation (ME) module configured to perform motion estimation by moving a search position toward the optimal initial search position output by the DP module.

Abstract: A method of image processing based on global motion estimation including: estimating global motion parameters corresponding to components of a global motion between a current image frame and a reference image frame by executing a global motion estimation model comprising one or more neural networks that input the current image frame and the reference image frame; generating a geometric transformation matrix by combining the global motion parameters; and generating at least one of an output image and an output video using the geometric transformation matrix.

Abstract: An image processing method, including: receiving an input image including a first image frame corresponding to a first time point and a second image frame corresponding to a second time point; inferring a plurality of parameters by applying the input image to a neural network model, wherein the plurality of parameters indicate global motion information including a three-dimensional (3D) motion of the input image and auxiliary information corresponding to at least one task using the global motion information; and outputting the plurality of parameters.

Abstract: A memory controller includes one or more processors including processing circuitry, and a memory storing instructions. The instructions, when executed by the one or more processors individually or collectively, cause the memory controller to generate latent data representations corresponding to data values to be written in a memory space by using an invertible neural network model, generate distribution parameters corresponding to the latent data representations by using a non-invertible neural network model, compress the latent data representations based on the distribution parameters, partially decompress at least one latent data representation from among the compressed latent data representations corresponding to at least one data value from among the data values written in the memory space, based on a command from a host device to provide the at least one data value, and provide, to the host device, the at least one data value.

Abstract: An image encoding apparatus may include a memory storing one or more instructions; and a processor configured to execute the one or more instructions to: obtain an initial search position from a student neural network that has been trained through a knowledge distillation from a teacher neural network by inputting a current frame and a reference frame to the student neural network; and perform motion estimation based on the initial search position.

Abstract: A video encoder is provided. The video encoder according to an example embodiment includes: a differentiable prediction (DP) module configured to output an optimal initial search position by performing full search in a predetermined area by using a pair of frames of a video as input; and a motion estimation (ME) module configured to perform motion estimation by moving a search position toward the optimal initial search position output by the DP module.

Abstract: An image encoding apparatus may include a memory storing one or more instructions; and a processor configured to execute the one or more instructions to: obtain an initial search position from a student neural network that has been trained through a knowledge distillation from a teacher neural network by inputting a current frame and a reference frame to the student neural network; and perform motion estimation based on the initial search position.

Abstract: A method of operating a wearable electronic device includes: recognizing a first gesture of a hand of a user for setting a region of interest (ROI) corresponding to a view of the user in an image frame corresponding to a view of a camera; generating a virtual display for projecting the ROI based on whether the first gesture is recognized; extracting the ROI from the image frame; recognizing a second gesture of the hand for adjusting a size of the ROI; and adjusting the size of the ROI and projecting the ROI of the adjusted size onto the virtual display, based on whether the second gesture is recognized.

Abstract: A neural codec includes a first simulated predictor for predicting a first block corresponding to a target block within a current frame, wherein the first block is predicted in accordance with the target block of the to-be-predicted current frame and pixels of neighbor blocks adjacent to the target block being input to the first simulated predictor, a second simulated predictor for predicting a second block corresponding to a target block using a reference block of a frame determined based on a prediction mode, wherein the second block is predicted in accordance with the reference block of a reference frame adjacent to the current frame and the target block being input to the second simulated predictor, and a selection network configured to select, based on the prediction mode, one of the first block and the second block as a predicted block.

Abstract: A method and apparatus for tracking hand joints are disclosed, where the method of tracking hand joints includes estimating angle information of finger joints based on initial positions of hand joints obtained from an image, generating a kinematic model of the hand joints based on the initial positions of the hand joints and the angle information of the finger joints, and tracking the hand joints by updating at least one of positions or angles of the hand joints based on the initial positions of the hand joints and the kinematic model.

Abstract: An image processing apparatus for performing motion estimation is provided. The image processing apparatus includes at least one processor configured to implement: a position estimation module configured to estimate an initial search position by providing a first frame and a second frame of a video as input to a neural network that is trained to output the initial search position; and a motion estimation module configured to perform motion estimation based on the initial search position.

Abstract: Disclosed is a pose identification method including obtaining a depth image of a target, obtaining feature information of the depth image and position information corresponding to the feature information, and obtaining a pose identification result of the target based on the feature information and the position information.

Abstract: Disclosed is a pose identification method including obtaining a depth image of a target, obtaining feature information of the depth image and position information corresponding to the feature information, and obtaining a pose identification result of the target based on the feature information and the position information.

Abstract: A neural codec includes a first simulated predictor for predicting a first block corresponding to a target block within a current frame, wherein the first block is predicted in accordance with the target block of the to-be-predicted current frame and pixels of neighbor blocks adjacent to the target block being input to the first simulated predictor, a second simulated predictor for predicting a second block corresponding to a target block using a reference block of a frame determined based on a prediction mode, wherein the second block is predicted in accordance with the reference block of a reference frame adjacent to the current frame and the target block being input to the second simulated predictor, and a selection network configured to select, based on the prediction mode, one of the first block and the second block as a predicted block.

Abstract: An electronic device for predicting a pose and a method of operating the electronic device are provided. The method includes extracting a feature map from an input image, predicting coordinates of a joint point from the feature map using an ordinal regression model, and predicting a pose of an object using the predicted coordinates of the joint point.

Abstract: An object pose and model estimation method includes acquiring a global feature of an input image, and a location code of an object including location information for a joint point of the object and location information for a model vertex in a template model; determining a local area feature of the object based on the global feature of the input image and based on the location code of the object in the template model; and acquiring location information for the joint point of the object in the input image and location information for the model vertex in the input image based on the local area feature of the object.

Abstract: A method of operating a wearable electronic device includes: recognizing a first gesture of a hand of a user for setting a region of interest (ROI) corresponding to a view of the user in an image frame corresponding to a view of a camera; generating a virtual display for projecting the ROI based on whether the first gesture is recognized; extracting the ROI from the image frame; recognizing a second gesture of the hand for adjusting a size of the ROI; and adjusting the size of the ROI and projecting the ROI of the adjusted size onto the virtual display, based on whether the second gesture is recognized.

Abstract: A method and apparatus for tracking hand joints are disclosed, where the method of tracking hand joints includes estimating angle information of finger joints based on initial positions of hand joints obtained from an image, generating a kinematic model of the hand joints based on the initial positions of the hand joints and the angle information of the finger joints, and tracking the hand joints by updating at least one of positions or angles of the hand joints based on the initial positions of the hand joints and the kinematic model.

Abstract: Disclosed is a pose identification method including obtaining a depth image of a target, obtaining feature information of the depth image and position information corresponding to the feature information, and obtaining a pose identification result of the target based on the feature information and the position information.

Abstract: An image processing apparatus includes an adaptive interpolation device which converts a MFA pattern image into a quincuncial pattern image based on difference values, and interpolates color channels and an NIR channel, based on difference values of the converted quincuncial pattern image in vertical and horizontal pixel directions; a frequency compensation device which obtains a high-resolution MFA image using high-frequency and medium-frequency components of a high-resolution base image, based on linear regression analysis and compared energy levels of MFA channel images to an energy level of a base image; and a channel interference suppression device which removes color distortion generated between each channel of the high-resolution MFA image, and another channel of the high-resolution MFA image and a base channel using a weighted average of pixel value differences between each channel of the high-resolution MFA image, and the other channel of the high-resolution MFA image and the base channel.