Some content of this application is unavailable at the moment.
If this situation persist, please contact us atFeedback&Contact
1. (WO2019009448) METHOD AND DEVICE FOR ENCODING OR DECODING IMAGE
Latest bibliographic data on file with the International Bureau    Submit observation

Pub. No.: WO/2019/009448 International Application No.: PCT/KR2017/007263
Publication Date: 10.01.2019 International Filing Date: 06.07.2017
IPC:
H04N 19/117 (2014.01) ,H04N 19/124 (2014.01) ,H04N 19/105 (2014.01) ,G06N 3/08 (2006.01)
[IPC code unknown for H04N 19/117][IPC code unknown for H04N 19/124][IPC code unknown for H04N 19/105]
G PHYSICS
06
COMPUTING; CALCULATING; COUNTING
N
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3
Computer systems based on biological models
02
using neural network models
08
Learning methods
Applicants:
삼성전자 주식회사 SAMSUNG ELECTRONICS CO., LTD. [KR/KR]; 경기도 수원시 영통구 삼성로 129 129, Samsung-ro, Yeongtong-gu, Suwon-si, Gyeonggi-do 16677, KR
Inventors:
박영오 PARK, Young-o; KR
김재환 KIM, Jae-hwan; KR
이종석 LEE, Jong-seok; KR
전선영 JEON, Sun-young; KR
박정훈 PARK, Jeong-hoon; KR
최광표 CHOI, Kwang-pyo; KR
Agent:
리앤목 특허법인 Y.P.LEE, MOCK & PARTNERS; 서울시 강남구 언주로30길 13 대림아크로텔 12층 12F Daelim Acrotel 13, Eonju-ro 30-gil, Gangnam-gu, Seoul 06292, KR
Priority Data:
Title (EN) METHOD AND DEVICE FOR ENCODING OR DECODING IMAGE
(FR) PROCÉDÉ ET DISPOSITIF DE CODAGE OU DE DÉCODAGE D'IMAGE
(KO) 영상을 부호화 또는 복호화하는 방법 및 장치
Abstract:
(EN) Disclosed is an in-loop filtering technique using a deep neural network (DNN). A method for decoding an image, according to one disclosed embodiment, comprises the steps of: receiving a bitstream of an encoded image; generating restoration data generated by restoring the encoded image; acquiring, from the bitstream, filter information for the restoration data; on the basis of the filter information, selecting, among predetermined DNN filter set candidates for in-loop filtering, a DNN filter set for compensating errors of the restoration data; and performing DNN-based in-loop filtering on the restoration data using the DNN filter set.
(FR) L'invention concerne une technique de filtrage en boucle utilisant un réseau neuronal profond (DNN). Un procédé de décodage d'une image, selon un mode de réalisation décrit, comprend les étapes consistant à : recevoir un train de bits d'une image codée ; générer des données de restauration générées par restauration de l'image codée ; acquérir, à partir du train de bits, des informations de filtre pour les données de restauration ; sur la base des informations de filtre, sélectionner, parmi des candidats d'ensemble de filtres DNN prédéterminés pour un filtrage en boucle, un ensemble de filtres DNN pour compenser des erreurs des données de restauration ; et effectuer un filtrage en boucle à base de DNN sur les données de restauration à l'aide de l'ensemble de filtres DNN.
(KO) DNN을 이용한 인루프 필터링 기술이 개시된다. 개시된 일 실시예에 따른 영상 복호화 방법은, 부호화된 영상의 비트스트림을 수신하는 단계, 상기 부호화된 영상을 복원한 복원 데이터를 생성하는 단계, 상기 비트스트림으로부터 상기 복원 데이터에 대한 필터 정보를 획득하는 단계, 상기 필터 정보에 기초하여, 미리 설정된 인루프 필터링에 대한 DNN(Deep Neural Network) 필터 세트 후보 중 상기 복원 데이터의 에러를 보상하기 위한 DNN 필터 세트를 선택하는 단계, 및 상기 DNN 필터 세트를 이용하여 상기 복원 데이터에 대하여 DNN에 기반한 인루프 필터링을 수행하는 단계를 포함한다.
front page image
Designated States: AE, AG, AL, AM, AO, AT, AU, AZ, BA, BB, BG, BH, BN, BR, BW, BY, BZ, CA, CH, CL, CN, CO, CR, CU, CZ, DE, DJ, DK, DM, DO, DZ, EC, EE, EG, ES, FI, GB, GD, GE, GH, GM, GT, HN, HR, HU, ID, IL, IN, IR, IS, JO, JP, KE, KG, KH, KN, KP, KR, KW, KZ, LA, LC, LK, LR, LS, LU, LY, MA, MD, ME, MG, MK, MN, MW, MX, MY, MZ, NA, NG, NI, NO, NZ, OM, PA, PE, PG, PH, PL, PT, QA, RO, RS, RU, RW, SA, SC, SD, SE, SG, SK, SL, SM, ST, SV, SY, TH, TJ, TM, TN, TR, TT, TZ, UA, UG, US, UZ, VC, VN, ZA, ZM, ZW
African Regional Intellectual Property Organization (ARIPO) (BW, GH, GM, KE, LR, LS, MW, MZ, NA, RW, SD, SL, ST, SZ, TZ, UG, ZM, ZW)
Eurasian Patent Office (AM, AZ, BY, KG, KZ, RU, TJ, TM)
European Patent Office (EPO) (AL, AT, BE, BG, CH, CY, CZ, DE, DK, EE, ES, FI, FR, GB, GR, HR, HU, IE, IS, IT, LT, LU, LV, MC, MK, MT, NL, NO, PL, PT, RO, RS, SE, SI, SK, SM, TR)
African Intellectual Property Organization (BF, BJ, CF, CG, CI, CM, GA, GN, GQ, GW, KM, ML, MR, NE, SN, TD, TG)
Publication Language: Korean (KO)
Filing Language: Korean (KO)