Patents by Inventor Gi-Mun Um
Gi-Mun Um has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20240146959Abstract: Disclosed are an image encoding method using a skip mode and a device using the method. The image encoding method may comprise the steps of: judging whether there is residual block data of a prediction target block on the basis of predetermined data indicating whether residual block data has been encoded; and, if there is residual block data, restoring the prediction target block on the basis of the residual block data and an intra-screen predictive value of the prediction target block. Consequently, encoding and decoding efficiency can be increased by carrying out the encoding and decoding of screen residual data only for prediction target blocks where there is a need for a residual data block in accordance with screen similarity.Type: ApplicationFiled: January 8, 2024Publication date: May 2, 2024Applicants: Electronics and Telecommunications Research Institute, UNIVERSITY-INDUSTRY COOPERATION GROUP OF KYUNG HEE UNIVERSITYInventors: Gun BANG, Won Sik CHEONG, Gi Mun UM, Nam Ho HUR, Gwang Hoon PARK, Kyung Yong KIM
-
Patent number: 11910013Abstract: Disclosed are an image encoding method using a skip mode and a device using the method. The image encoding method may comprise the steps of: judging whether there is residual block data of a prediction target block on the basis of predetermined data indicating whether residual block data has been encoded; and, if there is residual block data, restoring the prediction target block on the basis of the residual block data and an intra-screen predictive value of the prediction target block. Consequently, encoding and decoding efficiency can be increased by carrying out the encoding and decoding of screen residual data only for prediction target blocks where there is a need for a residual data block in accordance with screen similarity.Type: GrantFiled: December 30, 2022Date of Patent: February 20, 2024Assignees: Electronics and Telecommunications Research Institute, UNIVERSITY-INDUSTRY COOPERATION GROUP OF KYUNG HEE UNIVERSITYInventors: Gun Bang, Won Sik Cheong, Gi Mun Um, Nam Ho Hur, Gwang Hoon Park, Kyung Yong Kim
-
Patent number: 11910014Abstract: Disclosed are an image encoding method using a skip mode and a device using the method. The image encoding method may comprise the steps of: judging whether there is residual block data of a prediction target block on the basis of predetermined data indicating whether residual block data has been encoded; and, if there is residual block data, restoring the prediction target block on the basis of the residual block data and an intra-screen predictive value of the prediction target block. Consequently, encoding and decoding efficiency can be increased by carrying out the encoding and decoding of screen residual data only for prediction target blocks where there is a need for a residual data block in accordance with screen similarity.Type: GrantFiled: December 30, 2022Date of Patent: February 20, 2024Assignees: Electronics and Telecommunications Research Institute, UNIVERSITY-INDUSTRY COOPERATION GROUP OF KYUNG HEE UNIVERSITYInventors: Gun Bang, Won Sik Cheong, Gi Mun Um, Nam Ho Hur, Gwang Hoon Park, Kyung Yong Kim
-
Patent number: 11902575Abstract: Disclosed are an image encoding method using a skip mode and a device using the method. The image encoding method may comprise the steps of: judging whether there is residual block data of a prediction target block on the basis of predetermined data indicating whether residual block data has been encoded; and, if there is residual block data, restoring the prediction target block on the basis of the residual block data and an intra-screen predictive value of the prediction target block. Consequently, encoding and decoding efficiency can be increased by carrying out the encoding and decoding of screen residual data only for prediction target blocks where there is a need for a residual data block in accordance with screen similarity.Type: GrantFiled: August 24, 2022Date of Patent: February 13, 2024Assignees: Electronics and Telecommunications Research Institute, UNIVERSITY-INDUSTRY COOPERATION GROUP OF KYUNG HEE UNIVERSITYInventors: Gun Bang, Won Sik Cheong, Gi Mun Um, Nam Ho Hur, Gwang Hoon Park, Kyung Yong Kim
-
Patent number: 11900561Abstract: A deep learning-based image stitching method and apparatus are provided. The deep learning-based image stitching method includes receiving a plurality of images including a first image and a second image stitched to the first image, extracting a feature map of the plurality of images, generating a plurality of flow maps indicating movement information of pixels of the plurality of images, based on the feature map, generating a plurality of warping images in which the pixels of the plurality of images are moved, by applying the plurality of flow maps to the plurality of images, respectively, generating a plurality of weight maps for blending the plurality of warping images, based on the feature map, and generating a stitch image in which the first image and the second image are stitched, by blending the plurality of warping images based on the plurality of weight maps.Type: GrantFiled: November 22, 2021Date of Patent: February 13, 2024Assignees: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE, THE INDUSTRY & ACADEMIC COOPERATION IN CHUNGNAM NATIONAL UNIVERSITYInventors: Gi Mun Um, Hee Kyung Lee, Dae-Young Song, Donghyeon Cho
-
Patent number: 11694303Abstract: Disclosed herein is a method of creating an image stitching workflow including acquiring 360-degree virtual reality (VR) image parameters necessary to makes a request for image stitching and create the image stitching workflow, acquiring a list of functions applicable to the image stitching workflow, creating the image stitching workflow based on functions selected from the list of functions, determining the number of media processing entities necessary to perform tasks configuring the image stitching workflow and generating a plurality of media processing entities according to the determined number of media processing entities, and allocating the tasks configuring the image stitching workflow to the plurality of media processing entities.Type: GrantFiled: March 18, 2020Date of Patent: July 4, 2023Assignee: Electronics and Telecommunications Research InstituteInventors: Hee Kyung Lee, Gi Mun Um, Jeong Il Seo, Seong Yong Lim, Joung Il Yun, Won Sik Cheong
-
Publication number: 20230156220Abstract: Disclosed are an image encoding method using a skip mode and a device using the method. The image encoding method may comprise the steps of: judging whether there is residual block data of a prediction target block on the basis of predetermined data indicating whether residual block data has been encoded; and, if there is residual block data, restoring the prediction target block on the basis of the residual block data and an intra-screen predictive value of the prediction target block. Consequently, encoding and decoding efficiency can be increased by carrying out the encoding and decoding of screen residual data only for prediction target blocks where there is a need for a residual data block in accordance with screen similarity.Type: ApplicationFiled: December 30, 2022Publication date: May 18, 2023Applicants: Electronics and Telecommunications Research Institute, UNIVERSITY-INDUSTRY COOPERATION GROUP OF KYUNG HEE UNIVERSITYInventors: Gun BANG, Won Sik CHEONG, Gi Mun UM, Nam Ho HUR, Gwang Hoon PARK, Kyung Yong KIM
-
Publication number: 20230133166Abstract: Disclosed are an image encoding method using a skip mode and a device using the method. The image encoding method may comprise the steps of: judging whether there is residual block data of a prediction target block on the basis of predetermined data indicating whether residual block data has been encoded; and, if there is residual block data, restoring the prediction target block on the basis of the residual block data and an intra-screen predictive value of the prediction target block. Consequently, encoding and decoding efficiency can be increased by carrying out the encoding and decoding of screen residual data only for prediction target blocks where there is a need for a residual data block in accordance with screen similarity.Type: ApplicationFiled: December 30, 2022Publication date: May 4, 2023Applicants: Electronics and Telecommunications Research Institute, UNIVERSITY-INDUSTRY COOPERATION GROUP OF KYUNG HEE UNIVERSITYInventors: Gun BANG, Won Sik CHEONG, Gi Mun UM, Nam Ho HUR, Gwang Hoon PARK, Kyung Yong KIM
-
Publication number: 20230098276Abstract: Disclosed herein are a method and apparatus for generating a panoramic image. The method includes configuring a data set for training a deep learning network based on K images, extracting an encoding feature map, a skip connection feature map, and a decoding feature map based on K/2 images, among the images, estimating multiple homographies based on the encoding feature map, estimating a flow adjustment map, a preprocessing blending map, a weight map, and a post-processing blending map based on the decoding feature map, deriving a flow map based on the multiple homographies and the flow adjustment map, generating a preprocessed image based on the preprocessing blending map, generating multiple warped images based on the preprocessed image and the flow map, generating a matching image based on the warped images and the weight map, and correcting the matching image based on the matching image and the post-processing blending map.Type: ApplicationFiled: September 23, 2022Publication date: March 30, 2023Applicants: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE, THE INDUSTRY & ACADEMIC COOPERATION IN CHUNGNAM NATIONAL UNIVERSITY (IAC)Inventors: Hee-Kyung LEE, Gi-Mun UM, Dae-Young SONG, Dong-Hyeon CHO
-
Publication number: 20220408111Abstract: Disclosed are an image encoding method using a skip mode and a device using the method. The image encoding method may comprise the steps of: judging whether there is residual block data of a prediction target block on the basis of predetermined data indicating whether residual block data has been encoded; and, if there is residual block data, restoring the prediction target block on the basis of the residual block data and an intra-screen predictive value of the prediction target block. Consequently, encoding and decoding efficiency can be increased by carrying out the encoding and decoding of screen residual data only for prediction target blocks where there is a need for a residual data block in accordance with screen similarity.Type: ApplicationFiled: August 24, 2022Publication date: December 22, 2022Applicants: Electronics and Telecommunications Research Institute, UNIVERSITY-INDUSTRY COOPERATION GROUP OF KYUNG HEE UNIVERSITYInventors: Gun BANG, Won Sik CHEONG, Gi Mun UM, Nam Ho HUR, Gwang Hoon PARK, Kyung Yong KIM
-
Patent number: 11523133Abstract: Disclosed are an image encoding method using a skip mode and a device using the method. The image encoding method may comprise the steps of: judging whether there is residual block data of a prediction target block on the basis of predetermined data indicating whether residual block data has been encoded; and, if there is residual block data, restoring the prediction target block on the basis of the residual block data and an intra-screen predictive value of the prediction target block. Consequently, encoding and decoding efficiency can be increased by carrying out the encoding and decoding of screen residual data only for prediction target blocks where there is a need for a residual data block in accordance with screen similarity.Type: GrantFiled: March 30, 2021Date of Patent: December 6, 2022Assignees: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE, UNIVERSITY-INDUSTRY COOPERATION GROUP OF KYUNG HEE UNIVERSITYInventors: Gun Bang, Won Sik Cheong, Gi Mun Um, Nam Ho Hur, Gwang Hoon Park, Kyung Yong Kim
-
Publication number: 20220222774Abstract: Disclosed herein are an apparatus and method for 360-degree video stitching. The apparatus for 360-degree video stitching includes memory for storing at least one program, and a processor for executing the program, wherein the program is configured to stitch features of multiple input images based on at least one parameter included in a 360-degree stitching function description template, and then creating a single 360-degree video, the 360-degree stitching function description template includes a configuration parameter that is an array of function parameters, the configuration parameter includes a stitching parameter, a camera parameter, a feature parameter, and a projection parameter, the feature parameter includes a method for extracting respective features from multiple input images, and the projection parameter includes a projection type that is a kind of a projection plane onto which the multiple input images are projected.Type: ApplicationFiled: January 11, 2022Publication date: July 14, 2022Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTEInventors: Gi-Mun UM, Seong-Yong LIM, Hee-Kyung LEE
-
Publication number: 20220164922Abstract: A deep learning-based image stitching method and apparatus are provided. The deep learning-based image stitching method includes receiving a plurality of images including a first image and a second image stitched to the first image, extracting a feature map of the plurality of images, generating a plurality of flow maps indicating movement information of pixels of the plurality of images, based on the feature map, generating a plurality of warping images in which the pixels of the plurality of images are moved, by applying the plurality of flow maps to the plurality of images, respectively, generating a plurality of weight maps for blending the plurality of warping images, based on the feature map, and generating a stitch image in which the first image and the second image are stitched, by blending the plurality of warping images based on the plurality of weight maps.Type: ApplicationFiled: November 22, 2021Publication date: May 26, 2022Inventors: Gi Mun UM, Hee Kyung LEE, Dae-Young SONG, Donghyeon CHO
-
Patent number: 11276142Abstract: Disclosed herein are an apparatus and method for synthesizing virtual viewpoint image. The apparatus for synthesizing virtual viewpoint images includes one or more processors, and an execution memory for storing at least one program that is executed by the one or more processors, wherein the at least one program is configured to receive multiple viewpoint images from cameras that capture images of multiple viewpoints, and back-project the multiple viewpoint images onto a world coordinate system in a three-dimensional (3D) space, generate warped images by performing triangular warping of projecting the multiple viewpoint images, back-projected onto the world coordinate system, onto a virtual viewpoint image coordinate system, and generate a finally synthesized virtual viewpoint image by blending the warped images.Type: GrantFiled: May 13, 2020Date of Patent: March 15, 2022Assignee: Electronics and Telecommunications Research InstituteInventors: Joung-Il Yun, Sang-Woon Kwak, Won-Sik Cheong, Gi-Mun Um
-
Publication number: 20210218993Abstract: Disclosed are an image encoding method using a skip mode and a device using the method. The image encoding method may comprise the steps of: judging whether there is residual block data of a prediction target block on the basis of predetermined data indicating whether residual block data has been encoded; and, if there is residual block data, restoring the prediction target block on the basis of the residual block data and an intra-screen predictive value of the prediction target block. Consequently, encoding and decoding efficiency can be increased by carrying out the encoding and decoding of screen residual data only for prediction target blocks where there is a need for a residual data block in accordance with screen similarity.Type: ApplicationFiled: March 30, 2021Publication date: July 15, 2021Applicants: Electronics and Telecommunications Research Institute, UNIVERSITY-INDUSTRY COOPERATION GROUP OF KYUNG HEE UNIVERSITYInventors: Gun BANG, Won Sik CHEONG, Gi Mun UM, Nam Ho HUR, Gwang Hoon PARK, Kyung Yong KIM
-
Patent number: 10992956Abstract: Disclosed are an image encoding method using a skip mode and a device using the method. The image encoding method may comprise the steps of: judging whether there is residual block data of a prediction target block on the basis of predetermined data indicating whether residual block data has been encoded; and, if there is residual block data, restoring the prediction target block on the basis of the residual block data and an intra-screen predictive value of the prediction target block. Consequently, encoding and decoding efficiency can be increased by carrying out the encoding and decoding of screen residual data only for prediction target blocks where there is a need for a residual data block in accordance with screen similarity.Type: GrantFiled: January 15, 2020Date of Patent: April 27, 2021Assignees: Electronics and Telecommunications Research Institute, University-Industry Cooperation Group of Kyung Hee UniversityInventors: Gun Bang, Won Sik Cheong, Gi Mun Um, Nam Ho Hur, Gwang Hoon Park, Kyung Yong Kim
-
Publication number: 20200410638Abstract: Disclosed herein are an apparatus and method for synthesizing virtual viewpoint image. The apparatus for synthesizing virtual viewpoint images includes one or more processors, and an execution memory for storing at least one program that is executed by the one or more processors, wherein the at least one program is configured to receive multiple viewpoint images from cameras that capture images of multiple viewpoints, and back-project the multiple viewpoint images onto a world coordinate system in a three-dimensional (3D) space, generate warped images by performing triangular warping of projecting the multiple viewpoint images, back-projected onto the world coordinate system, onto a virtual viewpoint image coordinate system, and generate a finally synthesized virtual viewpoint image by blending the warped images.Type: ApplicationFiled: May 13, 2020Publication date: December 31, 2020Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTEInventors: JOUNG-IL YUN, Sang-Woon KWAK, Won-Sik CHEONG, Gi-Mun UM
-
Patent number: 10825185Abstract: The present invention relates to a method and apparatus for performing object segmentation in an image. More particularly, the present invention divides a screen of an input image into at least two sub-images, and generates one image by combining the at least two sub-images to which an image segmentation algorithm is respectively applied.Type: GrantFiled: November 28, 2018Date of Patent: November 3, 2020Assignee: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTEInventors: Kwang Yong Kim, Sang Joon Park, Gi Mun Um, Chang Eun Lee
-
Publication number: 20200302575Abstract: Disclosed herein is a method of creating an image stitching workflow including acquiring 360-degree virtual reality (VR) image parameters necessary to makes a request for image stitching and create the image stitching workflow, acquiring a list of functions applicable to the image stitching workflow, creating the image stitching workflow based on functions selected from the list of functions, determining the number of media processing entities necessary to perform tasks configuring the image stitching workflow and generating a plurality of media processing entities according to the determined number of media processing entities, and allocating the tasks configuring the image stitching workflow to the plurality of media processing entities.Type: ApplicationFiled: March 18, 2020Publication date: September 24, 2020Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTEInventors: Hee Kyung LEE, Gi Mun UM, Jeong Il SEO, Seong Yong LIM, Joung Il YUN, Won Sik CHEONG
-
Publication number: 20200288102Abstract: Provided are an image processing method and apparatus for generating a three-dimensional (3D) virtual viewpoint image by combining multi-view depth map on a 3D space through depth clustering. In the image processing method and apparatus, pieces of color and depth information are stored in units of depth clusters to minimize influences of occlusion regions and holes during generating of the virtual viewpoint image.Type: ApplicationFiled: February 24, 2020Publication date: September 10, 2020Applicant: Electronics and Telecommunications Research InstituteInventors: Gi Mun UM, Joung Il YUN