Patents by Inventor Mun-churl Kim
Mun-churl Kim 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: 20210344916Abstract: Disclosed according to one exemplary embodiment includes not limited to: a filtering unit configured to generate filtering information by filtering a residual image corresponding to a difference between an original image and a prediction image; an inverse filtering unit configured to generate inverse filtering information by inversely filtering the filtering information; an estimator configured to generate the prediction image based on the original image and reconstruction information; a CNN-based in-loop filter configured to receive the inverse filtering information and the prediction image and to output the reconstruction information; and an encoder configured to perform encoding based on the filtering information and information of the prediction image, and wherein the CNN-based in-loop filter is trained for each of the plurality of artefact sections according to an artefact value or for each of the plurality of quantization parameter sections according to a quantization parameter.Type: ApplicationFiled: July 15, 2021Publication date: November 4, 2021Applicant: KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGYInventor: Mun Churl KIM
-
Publication number: 20210329307Abstract: Disclosed are a method of encoding a division block in video encoding and a method of decoding a division block in video decoding. An input picture is divided into encoding unit blocks. The encoding unit blocks are divided into sub-blocks. The sub-blocks are encoded by selectively using at least one of intra prediction encoding and inter prediction encoding. A decoding process is performed through a reverse process of the encoding method. When pixel values of an encoding unit block are encoded in video encoding, the flexibility in selecting an encoding mode is increased and the efficiency of encoding is increased.Type: ApplicationFiled: June 29, 2021Publication date: October 21, 2021Applicants: KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGY, KOREAN BROADCASTING SYSTEMInventors: Mun Churl KIM, Bum Shik LEE, Jae Il KIM, Chang Seob PARK, Sang Jin HAHM, In Joon CHO, Keun Sik LEE, Byung Sun KIM
-
Patent number: 11095887Abstract: Disclosed are an encoding device and a decoding device, which include a CNN-based in-loop filter. The encoding device according to one embodiment comprises: a filtering unit for generating filtering information by filtering a residual image corresponding to a difference between an original image and a prediction image; an inverse filtering unit for generating inverse filtering information by inversely filtering the filtering information; a prediction unit for generating the prediction image on the basis of the original image and reconstruction information; a CNN-based in-loop filter for receiving the inverse filtering information and the prediction image so as to output the reconstruction information; and an encoding unit for performing encoding on the basis of the filtering information and information of the prediction image.Type: GrantFiled: February 13, 2017Date of Patent: August 17, 2021Assignee: KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGYInventor: Mun Churl Kim
-
Patent number: 11076175Abstract: Disclosed are a method of encoding a division block in video encoding and a method of decoding a division block in video decoding. An input picture is divided into encoding unit blocks. The encoding unit blocks are divided into sub-blocks. The sub-blocks are encoded by selectively using at least one of intra prediction encoding and inter prediction encoding. A decoding process is performed through a reverse process of the encoding method. When pixel values of an encoding unit block are encoded in video encoding, the flexibility in selecting an encoding mode is increased and the efficiency of encoding is increased.Type: GrantFiled: September 17, 2019Date of Patent: July 27, 2021Assignees: Korea Advanced Institute of Science and Technology, Korean Broadcasting SystemInventors: Mun Churl Kim, Bum Shik Lee, Jae Il Kim, Chang Seob Park, Sang Jin Hahm, In Joon Cho, Keun Sik Lee, Byung Sun Kim
-
Patent number: 11057585Abstract: Disclosed are an image processing method and device using a line-wise operation. The image processing device, according to one embodiment, comprises: a receiver for receiving two-dimensional pixel information; at least one first line buffer for outputting the two-dimensional pixel information into a line-wise data line; an operator for performing a convolution operation on the basis of the data line data; and at least one second line buffer for outputting the data line on which the operation has been performed.Type: GrantFiled: December 12, 2018Date of Patent: July 6, 2021Assignee: Korea Advanced Institute of Science and TechnologyInventors: Mun Churl Kim, Yong Woo Kim, Jae Seok Choi
-
Publication number: 20210166360Abstract: Inverse tone mapping (ITM) aims at generating a single high dynamic range (HDR) image from a low dynamic range (LDR) image. While ITM was frequently used for graphics rendering in the HDR space, the advent of HDR consumer displays (e.g., HDR TV) and the consequent need for HDR multimedia contents open up new horizons for the consumption of ultra-high quality video contents. However, due to the lack of HDR-filmed contents, the legacy LDR videos must be up-converted for viewing on these HDR displays. Unfortunately, the previous ITM methods are not appropriate for HDR consumer displays, and their inverse-tone-mapped results are not visually pleasing with noise amplification or lack of details. In this paper, we propose a convolutional neural network (CNN) based architecture designed for the ITM to HDR consumer displays, called ITM-CNN, and its training strategy for enhancing the performance based on image decomposition using the guided filter.Type: ApplicationFiled: December 6, 2017Publication date: June 3, 2021Applicant: KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGYInventors: Mun Churl KIM, Soo Ye KIM, Dae Eun KIM
-
Publication number: 20210082087Abstract: Disclosed are an image processing method and device using a line-wise operation. The image processing device, according to one embodiment, comprises: a receiver for receiving an image; at least one first line buffer for outputting the image into a line-wise image line; a first convolution operator for generating a feature map by performing a convolution operation on the basis of the output from the first line buffer; and a feature map processor for storing the output from the first convolution operator in units of at least one line, and processing so as to output the feature map stored in units of at least one line into a two-dimensional form, wherein at least one convolution operation operates in the form of a pipeline.Type: ApplicationFiled: December 12, 2018Publication date: March 18, 2021Applicant: Korea Advanced Institute of Science and TechnologyInventors: Mun Churl KIM, Yong Woo KIM, Jae Seok CHOI
-
Publication number: 20210065334Abstract: Disclosed are an image processing method and device using a line-wise operation. The image processing device, according to one embodiment, comprises: a receiver for receiving an image; a first convolution operator for generating a feature map by performing a convolution operation on the basis of the image; and a compressor for compressing the feature map into units of at least one line; and a decompressor for reconstructing the feature map compressed into units of lines.Type: ApplicationFiled: December 12, 2018Publication date: March 4, 2021Applicant: Korea Advanced Institute of Science and TechnologyInventors: Mun Churl KIM, Yong Woo KIM, Jae Seok CHOI
-
Publication number: 20200336699Abstract: Disclosed are an image processing method and device using a line-wise operation. The image processing device, according to one embodiment, comprises: a receiver for receiving two-dimensional pixel information; at least one first line buffer for outputting the two-dimensional pixel information into a line-wise data line; an operator for performing a convolution operation on the basis of the data line data; and at least one second line buffer for outputting the data line on which the operation has been performed.Type: ApplicationFiled: December 12, 2018Publication date: October 22, 2020Applicant: Korea Advanced Institute of Science and TechnologyInventors: Mun Churl KIM, Yong Woo KIM, Jae Seok CHOI
-
Publication number: 20200311870Abstract: Provided are a method and an apparatus for performing scalable video decoding, wherein the method and the apparatus down-sample input video, determine the down-sampled input video as base layer video, generate prediction video for enhancement layer video by applying an up-scaling filter to the base layer video, and code the base layer video and the prediction video, wherein the up-scaling filter is a convolution filter of a deep neural network.Type: ApplicationFiled: March 27, 2020Publication date: October 1, 2020Inventors: Ju Hyun JUNG, Dong Hyun KIM, No Hyeok PARK, Jeung Won CHOI, Dae Eun KIM, Se Hwan KI, Mun Churl KIM, Ki Nam JUN, Seung Ho BAEK, Jong Hwan KO
-
Publication number: 20200252638Abstract: Disclosed decoding method of the intra prediction mode comprises the steps of: determining whether an intra prediction mode of a present prediction unit is the same as a first candidate intra prediction mode or as a second candidate intra prediction mode on the basis of 1-bit information; and determining, among said first candidate intra prediction mode and said second candidate intra prediction mode, which candidate intra prediction mode is the same as the intra prediction mode of said present prediction unit on the basis of additional 1-bit information, if the intra prediction mode of the present prediction unit is the same as at least either the first candidate intra prediction mode or the second candidate intra prediction mode, and decoding the intra prediction mode of the present prediction unit.Type: ApplicationFiled: April 24, 2020Publication date: August 6, 2020Applicants: Electronics and Telecommunications Research Institute, KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGYInventors: Jong Ho KIM, Hui Yong KIM, Se Yoon JEONG, Sung Chang LIM, Ha Hyun LEE, Jin Ho LEE, Suk Hee CHO, Jin Soo CHOI, Jin Woong KIM, Chie Teuk AHN, Mun Churl KIM, Bum Shik LEE
-
Patent number: 10674169Abstract: Disclosed decoding method of the intra prediction mode comprises the steps of: determining whether an intra prediction mode of a present prediction unit is the same as a first candidate intra prediction mode or as a second candidate intra prediction mode on the basis of 1-bit information; and determining, among said first candidate intra prediction mode and said second candidate intra prediction mode, which candidate intra prediction mode is the same as the intra prediction mode of said present prediction unit on the basis of additional 1-bit information, if the intra prediction mode of the present prediction unit is the same as at least either the first candidate intra prediction mode or the second candidate intra prediction mode, and decoding the intra prediction mode of the present prediction unit.Type: GrantFiled: September 18, 2018Date of Patent: June 2, 2020Assignees: Electronics and Telecommunications Research Institute, KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGYInventors: Jong Ho Kim, Hui Yong Kim, Se Yoon Jeong, Sung Chang Lim, Ha Hyun Lee, Jin Ho Lee, Suk Hee Cho, Jin Soo Choi, Jin Woong Kim, Chie Teuk Ahn, Mun Churl Kim, Bum Shik Lee
-
Patent number: 10664961Abstract: The present invention provides a technology that separates a low-contrast-ratio image into sublayer images, classifies each sublayer image into several categories in accordance with the characteristics of each sublayer image, and learns a transformation matrix representing a relationship between the low-contrast-ratio image and a high-contrast-ratio image for each category. In addition, the present invention provides a technology that separates an input low-contrast-ratio image into sublayer images, selects a category corresponding to each sublayer image, and applies a learned transformation matrix to generate a high.Type: GrantFiled: June 27, 2017Date of Patent: May 26, 2020Assignees: SILICON WORKS CO., LTD., Korea Advanced Institute of Science and TechnologyInventors: Yong Woo Kim, Sang Yeon Kim, Woo Suk Ha, Mun Churl Kim, Dae Eun Kim
-
Patent number: 10567782Abstract: Disclosed decoding method of the intra prediction mode comprises the steps of: determining whether an intra prediction mode of a present prediction unit is the same as a first candidate intra prediction mode or as a second candidate intra prediction mode on the basis of 1-bit information; and determining, among said first candidate intra prediction mode and said second candidate intra prediction mode, which candidate intra prediction mode is the same as the intra prediction mode of said present prediction unit on the basis of additional 1-bit information, if the intra prediction mode of the present prediction unit is the same as at least either the first candidate intra prediction mode or the second candidate intra prediction mode, and decoding the intra prediction mode of the present prediction unit.Type: GrantFiled: September 18, 2018Date of Patent: February 18, 2020Assignees: Electronics and Telecommunications Research Institute, Korea Advanced Institute of Science and TechnologyInventors: Jong Ho Kim, Hui Yong Kim, Se Yoon Jeong, Sung Chang Lim, Ha Hyun Lee, Jin Ho Lee, Suk Hee Cho, Jin Soo Choi, Jin Woong Kim, Chie Teuk Ahn, Mun Churl Kim, Bum Shik Lee
-
Patent number: 10560709Abstract: Disclosed decoding method of the intra prediction mode comprises the steps of: determining whether an intra prediction mode of a present prediction unit is the same as a first candidate intra prediction mode or as a second candidate intra prediction mode on the basis of 1-bit information; and determining, among said first candidate intra prediction mode and said second candidate intra prediction mode, which candidate intra prediction mode is the same as the intra prediction mode of said present prediction unit on the basis of additional 1-bit information, if the intra prediction mode of the present prediction unit is the same as at least either the first candidate intra prediction mode or the second candidate intra prediction mode, and decoding the intra prediction mode of the present prediction unit.Type: GrantFiled: September 18, 2018Date of Patent: February 11, 2020Assignees: Electronics and Telecommunications Research Institute, Korea Advanced Institute of Science and TechnologyInventors: Jong Ho Kim, Hui Yong Kim, Se Yoon Jeong, Sung Chang Lim, Ha Hyun Lee, Jin Ho Lee, Suk Hee Cho, Jin Soo Choi, Jin Woong Kim, Chie Teuk Ahn, Mun Churl Kim, Bum Shik Lee
-
Publication number: 20200014957Abstract: Disclosed are a method of encoding a division block in video encoding and a method of decoding a division block in video decoding. An input picture is divided into encoding unit blocks. The encoding unit blocks are divided into sub-blocks. The sub-blocks are encoded by selectively using at least one of intra prediction encoding and inter prediction encoding. A decoding process is performed through a reverse process of the encoding method. When pixel values of an encoding unit block are encoded in video encoding, the flexibility in selecting an encoding mode is increased and the efficiency of encoding is increased.Type: ApplicationFiled: September 17, 2019Publication date: January 9, 2020Applicants: KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGY, KOREAN BROADCASTING SYSTEMInventors: Mun Churl KIM, Bum Shik LEE, Jae Il KIM, Chang Seob PARK, Sang Jin HAHM, In Joon CHO, Keun Sik LEE, Byung Sun KIM
-
Patent number: 10531123Abstract: An image decoding method based on a low-complexity transformation is provided. The method comprises: executing a transformation with respect to a residual block based on a first transformation kernel, and executing a transformation with respect to the transformed residual block based on a second transformation kernel having low-complexity, wherein the first transformation kernel is derived based on a prediction block or an encoding unit block.Type: GrantFiled: December 21, 2015Date of Patent: January 7, 2020Assignee: Korea Advanced Institute of Science and TechnologyInventors: Mun Churl Kim, Bum Shik Lee
-
Patent number: 10469840Abstract: Provided is a video encoding apparatus, including a signal separator to separate a differential image block into a first domain and a second domain, based on a boundary line included in the differential image block, the differential image block indicating a difference between an original image and a prediction image with respect to the original image, a transform encoder to perform a transform encoding with respect to the first domain using a discrete cosine transform (DCT), a quantization unit to quantize an output of the transform encoding unit in a frequency domain, a space domain quantization unit to quantize the second domain in a space domain, and an entropy encoder to perform an entropy encoding using outputs of the quantization unit and the space domain quantization unit.Type: GrantFiled: March 22, 2018Date of Patent: November 5, 2019Assignees: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE, KWANGWOON UNIVERSITY INDUSTRY-ACADEMIC COLLABORATION FOUNDATION, KOREA-INDUSTRY COOPERATION GROUP OF KYUNG HEE UNIVERSITY, KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGYInventors: Sung-Chang Lim, Ha Hyun Lee, Hui Yong Kim, Se Yoon Jeong, Suk Hee Cho, Hae Chul Choi, Jong Ho Kim, Jin Ho Lee, Jin Soo Choi, Jin Woo Hong, Dong Gyu Sim, Seoung Jun Oh, Gwang Hoon Park, Mun Churl Kim, Neung Joo Hwang, Sea Nae Park
-
Patent number: 10462494Abstract: Disclosed are a method of encoding a division block in video encoding and a method of decoding a division block in video decoding. An input picture is divided into encoding unit blocks. The encoding unit blocks are divided into sub-blocks. The sub-blocks are encoded by selectively using at least one of intra prediction encoding and inter prediction encoding. A decoding process is performed through a reverse process of the encoding method. When pixel values of an encoding unit block are encoded in video encoding, the flexibility in selecting an encoding mode is increased and the efficiency of encoding is increased.Type: GrantFiled: December 27, 2017Date of Patent: October 29, 2019Assignees: Korea Advanced Institute of Science and Technology, Korean Broadcasting SystemInventors: Mun Churl Kim, Bum Shik Lee, Jae Il Kim, Chang Seob Park, Sang Jin Hahm, In Joon Cho, Keun Sik Lee, Byung Sun Kim
-
Publication number: 20190230354Abstract: Disclosed are an encoding device and a decoding device, which include a CNN-based in-loop filter. The encoding device according to one embodiment comprises: a filtering unit for generating filtering information by filtering a residual image corresponding to a difference between an original image and a prediction image; an inverse filtering unit for generating inverse filtering information by inversely filtering the filtering information; a prediction unit for generating the prediction image on the basis of the original image and reconstruction information; a CNN-based in-loop filter for receiving the inverse filtering information and the prediction image so as to output the reconstruction information; and an encoding unit for performing encoding on the basis of the filtering information and information of the prediction image.Type: ApplicationFiled: February 13, 2017Publication date: July 25, 2019Applicant: KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGYInventor: Mun Churl KIM