[go: up one dir, main page]

WO2022114669A3 - Image encoding using neural network - Google Patents

Image encoding using neural network Download PDF

Info

Publication number
WO2022114669A3
WO2022114669A3 PCT/KR2021/016973 KR2021016973W WO2022114669A3 WO 2022114669 A3 WO2022114669 A3 WO 2022114669A3 KR 2021016973 W KR2021016973 W KR 2021016973W WO 2022114669 A3 WO2022114669 A3 WO 2022114669A3
Authority
WO
WIPO (PCT)
Prior art keywords
neural network
image encoding
encoding
image
video
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/KR2021/016973
Other languages
French (fr)
Korean (ko)
Other versions
WO2022114669A2 (en
Inventor
박상효
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Industry Academic Cooperation Foundation of KNU
Original Assignee
Industry Academic Cooperation Foundation of KNU
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Priority claimed from KR1020210030727A external-priority patent/KR102466258B1/en
Application filed by Industry Academic Cooperation Foundation of KNU filed Critical Industry Academic Cooperation Foundation of KNU
Publication of WO2022114669A2 publication Critical patent/WO2022114669A2/en
Publication of WO2022114669A3 publication Critical patent/WO2022114669A3/en
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T9/00—Image coding

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Compression Or Coding Systems Of Tv Signals (AREA)

Abstract

As a disclosure relating to a method for encoding an image (video) by using a neural network, the present embodiment provides an image encoding method for performing versatile video coding (VVC), wherein a ternary tree is determined among multi-type trees (MTTs) by using a light-weight neural network (LNN) on the basis of an explicit attribute and a derivative attribute extracted in a coding unit (CU) encoding process, in order to reduce computational complexity for intra prediction.
PCT/KR2021/016973 2020-11-25 2021-11-18 Image encoding using neural network Ceased WO2022114669A2 (en)

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
KR20200159984 2020-11-25
KR10-2020-0159984 2020-11-25
KR10-2021-0030727 2021-03-09
KR1020210030727A KR102466258B1 (en) 2020-11-25 2021-03-09 Video Encoding Using Neural Network

Publications (2)

Publication Number Publication Date
WO2022114669A2 WO2022114669A2 (en) 2022-06-02
WO2022114669A3 true WO2022114669A3 (en) 2022-07-21

Family

ID=81756163

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2021/016973 Ceased WO2022114669A2 (en) 2020-11-25 2021-11-18 Image encoding using neural network

Country Status (1)

Country Link
WO (1) WO2022114669A2 (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20170041857A (en) * 2014-08-26 2017-04-17 리리컬 랩스 비디오 컴프레션 테크놀로지, 엘엘씨 Learning-based partitioning for video encoding
KR20180083030A (en) * 2017-01-11 2018-07-20 한국전자통신연구원 Convolutional neural network system having binary parameter and operation method thereof

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20170041857A (en) * 2014-08-26 2017-04-17 리리컬 랩스 비디오 컴프레션 테크놀로지, 엘엘씨 Learning-based partitioning for video encoding
KR20180083030A (en) * 2017-01-11 2018-07-20 한국전자통신연구원 Convolutional neural network system having binary parameter and operation method thereof

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
JIN ZHIPENG; AN PING; YANG CHAO; SHEN LIQUAN: "Fast QTBT Partition Algorithm for Intra Frame Coding through Convolutional Neural Network", IEEE ACCESS, IEEE, USA, vol. 6, 1 January 1900 (1900-01-01), USA , pages 54660 - 54673, XP011693102, DOI: 10.1109/ACCESS.2018.2872492 *
PARK SANG-HYO: "Fast Decision Method of Adaptive Motion Vector Resolution", JOURNAL OF BROADCAST ENGINEERING, KOREA, vol. 25, no. 3, 1 May 2020 (2020-05-01), Korea , pages 305 - 312, XP055951343, ISSN: 1226-7953, DOI: 10.5909/JBE.2020.25.3.305 *
PARK SANG-HYO; KANG JE-WON: "Context-Based Ternary Tree Decision Method in Versatile Video Coding for Fast Intra Coding", IEEE ACCESS, IEEE, USA, vol. 7, 1 January 1900 (1900-01-01), USA , pages 172597 - 172605, XP011759036, DOI: 10.1109/ACCESS.2019.2956196 *

Also Published As

Publication number Publication date
WO2022114669A2 (en) 2022-06-02

Similar Documents

Publication Publication Date Title
ZA202107294B (en) Using interpolation filters for history based motion vector prediction
CN104683804B (en) Parameter adaptive multidimensional bit rate control method based on video content features
DE102019218837A1 (en) METHOD AND SYSTEMS FOR THE NEURONAL NETWORK FACTORY LOOP FILTERING FOR VIDEO CODING
WO2018223822A1 (en) Pruning- and distillation-based convolutional neural network compression method
CN110087087A (en) VVC interframe encode unit prediction mode shifts to an earlier date decision and block divides and shifts to an earlier date terminating method
CN104219525B (en) Perception method for video coding based on conspicuousness and minimum discernable distortion
EP4283999A3 (en) Video decoding method, and video decoder
MY205810A (en) Apparatus and method for filtering in video coding
CN107040782B (en) Video coding overall situation Rate-distortion optimization method based on Lagrangian method
DE112012000397T5 (en) Video encoding system using implied reference frames
WO2022114669A3 (en) Image encoding using neural network
CN105898300A (en) Improved transformation coefficient sign data hiding method based on recovered transformation coefficient
CN105554502A (en) Distributed compressed sensing video encoding and decoding method based on foreground-background separation
CN105357523A (en) High-order singular value decomposition (HOSVD) algorithm based video compression system and method
MX2025010064A (en) Prediction weighted table-based image/video coding method and apparatus
MX2025003671A (en) Image decoding method using chroma quantization parameter, and apparatus therefor
CN101309426A (en) Anti-error method of video telephony video transmission based on face detection
CN111787218A (en) Monitoring camera based on digital retina technology
CN102752598A (en) Fast adaptive code rate control method
CN104488266B (en) AVS Video Compression Encoding Method and Encoder
Eimon et al. Enabling Next-Generation Consumer Experience with Feature Coding for Machines
Chen et al. Transformer-based learned image compression for joint decoding and denoising
CN110572661B (en) Low-delay code rate control method for 4K/8K ultra-high-definition video coding
CN106791864B (en) An implementation method of improving video transcoding rate based on HEVC standard
Cai et al. Efficient Semantic Segmentation for Compressed Video

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21898495

Country of ref document: EP

Kind code of ref document: A2

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21898495

Country of ref document: EP

Kind code of ref document: A2