-
公开(公告)号：US11887330B2
公开(公告)日：2024-01-30
申请号：US17848813
申请日：2022-06-24
Inventor： Junyong Noh , Hyunggoog Seo , Jaedong Kim , Kwanggyoon Seo , Bumki Kim
IPC: G06T7/73 , G06F3/01 , G06F3/03 , G06F3/0484
CPC classification number: G06T7/73 , G06F3/012 , G06F3/017 , G06F3/03 , G06F3/0484
Abstract: A method of assisting object registration in a smart home system including a plurality of objects is disclosed. The disclosed method may include allowing a user to select an object from among a plurality of objects, capturing a plurality of pointing gestures by allowing the user to perform the plurality of pointing gestures at the selected object, configuring a pointing ray using each of the plurality of captured pointing gestures, estimating a position of a nearest point extending from the plurality of pointing rays, and registering the estimated position of the nearest point as a position of the selected object.
-
公开(公告)号：US20220101488A1
公开(公告)日：2022-03-31
申请号：US17429254
申请日：2019-02-21
Inventor： Junyong Noh , Hanui Lee , Bumki Kim , Gukho Kim , Julie Alfonsine E. Lelong , Mohammad Reza Karimi Dastjerdi , Allen Kim , Jiwon Lee
Abstract: An image processing device according to one embodiment estimates optical flow information, pixel by pixel, on the basis of a reference image and input images of consecutive frames, and estimates a term corresponding to temporal consistency between the frames of the input images. The image processing device determines a mesh on the basis of the term corresponding to temporal consistency and the optical flow information, and transforms the reference image on the basis of the mesh. The image processing device preforms image blending on the basis of the input image, the transformed reference image, and mask data.
-
3.发明申请公开(公告)号：US20180368734A1
公开(公告)日：2018-12-27
申请号：US16015474
申请日：2018-06-22
Inventor： Junyong Noh , Sunjin Jung , Seokpyo Hong , Kyungmin Cho , Haegwang Eom , Byung Kuk Choi
Abstract: An apparatus for motion transformation according to an embodiment of the present disclosure includes a basic data input unit through which basic motion data is inputted, a pre-processing unit which acquires a parameter through pre-processing of the inputted basic motion data, a motion transformation unit which performs biomechanical observations-based gait motion transformation processing based on the pre-processed parameter and age input information, and an output unit which outputs the transformation processed motion.
-
公开(公告)号：US20180165860A1
公开(公告)日：2018-06-14
申请号：US15838494
申请日：2017-12-12
Inventor： Junyong Noh , Byungkuk Choi , Roger Blanco i Ribera , Seokpyo Hong , Haegwang Eom , Sunjin Jung , J. P. Lewis , Yeongho Seol
IPC: G06T13/20 , G06F3/0488 , G06F3/0484
CPC classification number: G06T13/20 , G06F3/04847 , G06F3/04883 , G06T13/40 , G06T19/20 , G06T2213/12 , G06T2219/2004
Abstract: The present disclosure relates to a motion edit method for editing the motion of an articulated object using a computing device with a touch screen, including a) when any one of a joint path and a body line of an articulated object is selected by a user, setting a position constraint of higher level joint according to the user's sketching input and joint hierarchy, and b) generating motion of the articulated object for which the constraint is set.
-
公开(公告)号：US20220155871A1
公开(公告)日：2022-05-19
申请号：US17242568
申请日：2021-04-28
Inventor： Junyong Noh , Haegwang Eom , ByungKuk Choi , Kyungmin Cho , Sunjin Jung , Seokpyo Hong
Abstract: A motion processing method and apparatus are provided. The motion processing method includes obtaining a base-level motion by applying a linear Gaussian model to an input motion, obtaining a controllable motion displacement vector and a residual motion displacement vector by applying the linear Gaussian model to a displacement vector between the input motion and the base-level motion, and synthesizing an output motion based on the base-level motion and the controllable motion displacement vector.
-
Patent Agency Ranking
6.发明授权公开(公告)号：US11282254B2
公开(公告)日：2022-03-22
申请号：US16940530
申请日：2020-07-28
Inventor： Junyong Noh , Haegwang Eom , Daseong Han , Sung Yong Shin
Abstract: Provided is a full-body modeling method and apparatus based on new model predictive control (MPC) with a visuomotor system in which visual perception and full-body motion control are integrated. The full-body modeling method includes determining a partial observation value associated with a state of an object based on a point of sight of a character, estimating the state of the object using the determined partial observation value based on a partially observable Markov decision process (POMDP), controlling a state of the character based on the estimated state of the object, and visualizing a motion of the character.
-
7.发明授权公开(公告)号：US10586306B2
公开(公告)日：2020-03-10
申请号：US15648030
申请日：2017-07-12
Inventor： Junyong Noh , Sangwoo Lee , Jungjin Lee , Kyehyun Kim , Bumki Kim
Abstract: The present disclosure relates to an immersive display apparatus and method for creation of a peripheral view image corresponding to an input video, the method comprising a pre-processing step of obtaining scene-space information at a main-view video signal corresponding to a first area, a pre-warping step of performing first warping to at least one neighborhood frame corresponding to a target frame included in the pro-processed video signal and determining an outlier from the result of the first warping, a sampling step of sampling at least one neighborhood frame to be used for extrapolation from the result of the first warping, a warping step of performing second warping to the sampled frame except for the outlier to generate a peripheral view image signal corresponding to a second area around the first area, and a blending step of blending the peripheral view image signal to the main-view video signal.
-
公开(公告)号：US20180165252A1
公开(公告)日：2018-06-14
申请号：US15832954
申请日：2017-12-06
Inventor： Junyong Noh , Jungjin Lee , Sangwoo Lee , Younghui Kim , Bumki Kim
CPC classification number: G06F17/18 , E04H3/22 , G06F17/5004 , G06F2217/16 , G06T17/20 , H04N9/3147 , H04N9/3185
Abstract: The present disclosure relates to a method and a device for estimating suitability as a multi-screen projecting type theatre and the method for estimating the suitability as the multi-screen projecting type theatre includes: creating a plurality of image representation models (M) respectively corresponding to a plurality of candidate theatres; calculating a total image representation model ({circumflex over (M)}total) corresponding to all of the plurality of candidate theatres; and calculating a deviation between the total image representation model ({circumflex over (M)}total) and each of the plurality of image representation models (M) of the target theatre and estimating theatre suitability of the target theatre based on the deviation when one target theatre is selected among the plurality of candidate theatres.
-
公开(公告)号：US12277670B2
公开(公告)日：2025-04-15
申请号：US18457499
申请日：2023-08-29
Inventor： Junyong Noh , Sanghun Park , Kwanggyoon Seo
IPC: G06K9/00 , G06N3/045 , G06N3/088 , G06T3/4007 , G06T3/4046 , G06T5/50
Abstract: Disclosed is an image processing method and apparatus. The image processing method includes extracting a content latent code and a style latent code for each of a plurality of input images, obtaining a content feature vector by calculating a weighted sum of content latent codes extracted from the input images based on a morphing control parameter, obtaining a style feature vector by calculating a weighted sum of style latent codes extracted from the input images based on the morphing control parameter, and generating a morphing image based on the content feature vector and the style feature vector.
-
公开(公告)号：US12182918B2
公开(公告)日：2024-12-31
申请号：US17847472
申请日：2022-06-23
Inventor： Junyong Noh , Ha Young Chang , Kwanggyoon Seo , Jung Eun Yoo
Abstract: A method of training a deep neural network for generating a cinemagraph is disclosed. The method may include preparing a foreground layer input by using an input video, preparing a background layer input by using the input video, providing a foreground layer output and a background layer output from the DNN by inputting, to the DNN, the foreground layer input and the background layer input, providing an output video by synthesizing the foreground layer output with the background layer output, and updating intrinsic parameters of the DNN a plurality of times, based on the input video, the foreground layer input, the foreground layer output, the background layer output, and the output video.
-
-
-
-
-
-
-
-
-
Search Results
30
records
(took 0.019 seconds)
