Abstract: The present invention relates to a method for creating a neural network model which can imitate retouching styles of a plurality of experts, and creating a black-and-white photo which gives aesthetics by inputting a color photo into the neural network model.

Abstract: The present invention which is a method for generating a scene structure using a neural network model applied to a baseline network performing an image processing task by a plug-and-play scheme by using the scene structure includes: generating a plurality of eigenvectors for an image according to an affinity matrix of the image; and generating the scene structure by convolutioning the plurality of eigenvectors, and outputting the scene structure to the baseline network.

Abstract: The present disclosure relates to a method of aligning images included in a focal stack and estimates depth information of an object in the images by extracting features of the aligned images, using a neural network model. A focal stack alignment method according to an embodiment of the present disclosure includes: calculating a relative Field of View (FoV) of a focal stack photographed by a photographing device using metadata of the photographing device; primarily aligning the focal stack on the basis of the relative FoV; determining a flow field of the focal stack using radial motion, horizontal motion, and vertical motion features of each of primarily aligned images; and secondarily aligning the focal stack using the flow field.

Abstract: The present disclosure relates to a method for sampling a random vector corresponding to an intention of a pedestrian non-stochastically or applying a social statistical element that the majority of pedestrians move in groups to training, in training a neural network model for pedestrian trajectory prediction.

Abstract: The present disclosure relates to a method of inferring an epipolar plane image and extrapolating a view of a target image using the epipolar plane image. A view extrapolation method using an epipolar plane image according to an embodiment of the present disclosure includes: creating an Epipolar Plane Image (EPI) using a target image and a depth map corresponding to the target image; creating a super-resolution EPI and a disparity of the EPI on the basis of the EPI; creating an EPI mask by warping the super-resolution EPI in accordance with the disparity; and creating a restored EPI by applying the EPI mask to the warped super-resolution EPI, and creating an extrapolated image for the target image using the restored EPI.

Abstract: Disclosed is a method for performing image convolution by considering a hierarchical relationship of hyperbolic feature vectors in a hyperbolic space. According to an embodiment of the present disclosure, an image convolution method in a hyperbolic space includes steps of embedding an image feature vector on a Euclidean space into a hyperbolic feature vector on a hyperbolic space, allocating a hierarchical weight on the hyperbolic feature vector based on a hierarchical property of the hyperbolic feature vector, and convolutioning the hyperbolic feature vector by applying the hierarchical weight.

Abstract: A pedestrian trajectory prediction apparatus includes a waypoint learning unit configured to learn waypoints on a trajectory for a pedestrian from a source to a destination and a corrected trajectory learning unit configured to learn a correction vector for correcting a trajectory connecting the source and the destination.