公开(公告)号：US20230037418A1

公开(公告)日：2023-02-09

申请号：US17848735

申请日：2022-06-24

Applicant: Korea Advanced Institute of Science and Technology

Inventor： Sung-Eui YOON ,  In Young CHO ,  Yuchi HUO

IPC: G06T15/06 ,  G06T5/00 ,  G06N3/08

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.

公开(公告)号：US20220366669A1

公开(公告)日：2022-11-17

申请号：US17538555

申请日：2021-11-30

Applicant: Korea Advanced Institute Of Science And Technology

Inventor： Sung-Eui YOON ,  Woobin IM ,  Tae Kyun KIM

IPC: G06V10/74 ,  G06V10/80 ,  G06N20/00

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.

公开(公告)号：US20230334764A1

公开(公告)日：2023-10-19

申请号：US18193769

申请日：2023-03-31

Applicant: Samsung Electronics Co., Ltd. ,  Korea Advanced Institute of Science and Technology

Inventor： Heesae LEE ,  Kyubeom HAN ,  Jaeyoon KIM ,  Sung-Eui YOON ,  Seeha LEE ,  Inwoo HA

IPC: G06T15/10 ,  G06T15/08 ,  G06T15/06 ,  G06T7/60 ,  G06T7/73 ,  G06T9/00 ,  H04N23/698

CPC classification number: G06T15/10 ,  G06T15/08 ,  G06T15/06 ,  G06T7/60 ,  G06T7/73 ,  G06T9/00 ,  H04N23/698 ,  G06T2207/20084 ,  G06T2207/20081

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.

公开(公告)号：US20180173239A1

公开(公告)日：2018-06-21

申请号：US15817421

申请日：2017-11-20

Applicant: KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGY

Inventor： Sung-Eui YOON ,  Youngsun KWON ,  Donghyuk KIM

IPC: G05D1/02 ,  G01S17/89 ,  B25J9/16

CPC classification number: G05D1/0214 ,  B25J9/1664 ,  G01S7/4808 ,  G01S17/89 ,  G05D1/0231 ,  Y10S901/46 ,  Y10S901/47

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.