Abstract: A computer system of unsupervised learning with deep similarity for optical flow estimation is provided. The computer system is configured to calculate deep similarity by using deep features extracted from a sequence of a plurality of images, and learning optical flow for the images based on the deep similarity.

Abstract: Disclosed is a method and system for separating and recalibrating a feature for adversarial robustness. A feature separation and recalibration method may include disentangling an input feature map into a first feature defined as a robust feature and a second feature defined as a non-robust feature, based on a robustness score; generating a recalibrated feature by recalibrating activation of the second feature; and generating an output feature map by combining the first feature and the recalibrated feature.

Abstract: Disclosed is a ray clustering learning method based on weakly-supervised learning for denoising using ray tracing. The ray clustering learning method is for learning a denoising model for removing noise from a rendered image through ray tracing, and includes extracting a feature of a simulated ray through the ray tracing and clustering the ray through contrastive learning for the feature.

Abstract: A method and apparatus with image processing are provided. A method includes determining sample points sampled on a camera ray, wherein the camera ray is based on view-generation information comprising a scene viewing-position and a scene-viewing direction, determining location statuses of the respective sample points based on a virtual cylindrical coordinate system defined by a center and a radius, projecting and rendering a value of a pixel corresponding to the camera ray by, according the location statuses, applying the view-generation information to a first neural network to generate a first rendering result and to a second neural network to generate a second rendering result, wherein the first neural network has been trained to generate foreground images and the second neural network has been trained to generate background images, and generating a rendered image based on blending the first rendering result and the second rendering result.

Abstract: Disclosed is a ray clustering learning method based on weakly-supervised learning for denoising using ray tracing. The ray clustering learning method is for learning a denoising model for removing noise from a rendered image through ray tracing, and includes extracting a feature of a simulated ray through the ray tracing and clustering the ray through contrastive learning for the feature.

Abstract: Various example embodiments provide a computer system of unsupervised learning with deep similarity for optical flow estimation and a method thereof. According to various example embodiments, the computer system may be configured to calculate deep similarity by using deep features extracted from a sequence of a plurality of images, and learn optical flow for the images based on the deep similarity. In other words, the computer system may learn deep learning model for estimating optical flow through unsupervised learning based on deep similarity for a sequence of a plurality of images. At this time, the computer system may learn optical flow by using a feature separation loss function obtained by dividing occlusion locations and non-occlusion locations on the deep similarity map.

Abstract: Disclosed is a method and system for diffraction-aware non-line of sight (NLOS) sound source localization (SSL) that may reconstruct an indoor space, may generate acoustic rays into the indoor space based on an audio signal collected from the indoor space, and may estimate a position of an NLOS sound source based on a point at which one of the acoustic rays is diffracted.

Abstract: A method and system for updates an occupancy map based on a first ray determined from a plurality of rays, as known as a super ray. The method of updating an occupancy map based on grids and octrees includes the step of generating a mapping line based on point clouds obtained from a sensor, determining a super ray by identifying a cell belonging to a plurality of cells forming the occupancy map and traversing an identical cell based on the generated mapping line, and updating the occupancy map by updating a cell through which the super ray corresponding to some of rays related to the plurality of cells forming the occupancy map passes.

Abstract: Disclosed is a method and system for diffraction-aware non-line of sight (NLOS) sound source localization (SSL) that may reconstruct an indoor space, may generate acoustic rays into the indoor space based on an audio signal collected from the indoor space, and may estimate a position of an NLOS sound source based on a point at which one of the acoustic rays is diffracted.

Abstract: Disclosed herein are a method and system for updating an occupancy map based on a super ray. The method of updating an occupancy map based on grids and octrees includes the step of generating a mapping line based on point clouds obtained from a sensor, generating a super ray by identifying a cell belonging to a plurality of cells forming the occupancy map and traversing an identical cell based on the generated mapping line, and updating the occupancy map by updating a cell through which the super ray corresponding to some of rays related to the plurality of cells forming the occupancy map passes.