KR20230078658A - 비디오 코딩을 위한 뉴럴 네트워크-기반 필터링 프로세스에서의 활성화 함수 설계 - Google Patents

비디오 코딩을 위한 뉴럴 네트워크-기반 필터링 프로세스에서의 활성화 함수 설계 Download PDF

Info

Publication number
KR20230078658A
KR20230078658A KR1020237009903A KR20237009903A KR20230078658A KR 20230078658 A KR20230078658 A KR 20230078658A KR 1020237009903 A KR1020237009903 A KR 1020237009903A KR 20237009903 A KR20237009903 A KR 20237009903A KR 20230078658 A KR20230078658 A KR 20230078658A
Authority
KR
South Korea
Prior art keywords
alpha
video
video data
block
cnn
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.)
Pending
Application number
KR1020237009903A
Other languages
English (en)
Korean (ko)
Inventor
홍타오 왕
지안레 천
마르타 카르체비츠
Original Assignee
퀄컴 인코포레이티드
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
Application filed by 퀄컴 인코포레이티드 filed Critical 퀄컴 인코포레이티드
Publication of KR20230078658A publication Critical patent/KR20230078658A/ko
Pending legal-status Critical Current

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N19/00Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
    • H04N19/42Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by implementation details or hardware specially adapted for video compression or decompression, e.g. dedicated software implementation
    • H04N19/436Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by implementation details or hardware specially adapted for video compression or decompression, e.g. dedicated software implementation using parallelised computational arrangements
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N19/00Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
    • H04N19/10Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
    • H04N19/102Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or selection affected or controlled by the adaptive coding
    • H04N19/117Filters, e.g. for pre-processing or post-processing
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/04Architecture, e.g. interconnection topology
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/04Architecture, e.g. interconnection topology
    • G06N3/045Combinations of networks
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/04Architecture, e.g. interconnection topology
    • G06N3/0464Convolutional networks [CNN, ConvNet]
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/04Architecture, e.g. interconnection topology
    • G06N3/048Activation functions
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T9/00Image coding
    • G06T9/002Image coding using neural networks
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N19/00Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
    • H04N19/10Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
    • H04N19/169Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding
    • H04N19/17Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object
    • H04N19/176Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a block, e.g. a macroblock
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N19/00Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
    • H04N19/10Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
    • H04N19/169Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding
    • H04N19/184Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being bits, e.g. of the compressed video stream
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N19/00Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
    • H04N19/70Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by syntax aspects related to video coding, e.g. related to compression standards
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N19/00Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
    • H04N19/80Details of filtering operations specially adapted for video compression, e.g. for pixel interpolation
    • H04N19/82Details of filtering operations specially adapted for video compression, e.g. for pixel interpolation involving filtering within a prediction loop

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • Computing Systems (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Molecular Biology (AREA)
  • Computational Linguistics (AREA)
  • General Engineering & Computer Science (AREA)
  • Biophysics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Biomedical Technology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Compression Or Coding Systems Of Tv Signals (AREA)
  • Picture Signal Circuits (AREA)
KR1020237009903A 2020-09-30 2021-09-30 비디오 코딩을 위한 뉴럴 네트워크-기반 필터링 프로세스에서의 활성화 함수 설계 Pending KR20230078658A (ko)

Applications Claiming Priority (5)

Application Number Priority Date Filing Date Title
US202063085936P 2020-09-30 2020-09-30
US63/085,936 2020-09-30
US17/489,459 2021-09-29
US17/489,459 US11647212B2 (en) 2020-09-30 2021-09-29 Activation function design in neural network-based filtering process for video coding
PCT/US2021/052950 WO2022072684A1 (en) 2020-09-30 2021-09-30 Activation function design in neural network-based filtering process for video coding

Publications (1)

Publication Number Publication Date
KR20230078658A true KR20230078658A (ko) 2023-06-02

Family

ID=80821961

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020237009903A Pending KR20230078658A (ko) 2020-09-30 2021-09-30 비디오 코딩을 위한 뉴럴 네트워크-기반 필터링 프로세스에서의 활성화 함수 설계

Country Status (7)

Country Link
US (2) US11647212B2 (https=)
EP (1) EP4222954A1 (https=)
JP (1) JP7787883B2 (https=)
KR (1) KR20230078658A (https=)
CN (1) CN116325729B (https=)
PH (1) PH12023550209A1 (https=)
WO (1) WO2022072684A1 (https=)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2025009938A1 (ko) * 2023-07-05 2025-01-09 엘지전자 주식회사 영상 부호화/복호화 방법, 비트스트림을 저장한 기록 매체 및 비트스트림을 전송하는 방법

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11647212B2 (en) 2020-09-30 2023-05-09 Qualcomm Incorporated Activation function design in neural network-based filtering process for video coding
US20220321919A1 (en) * 2021-03-23 2022-10-06 Sharp Kabushiki Kaisha Systems and methods for signaling neural network-based in-loop filter parameter information in video coding
US12167047B2 (en) * 2022-01-13 2024-12-10 Tencent America LLC Neural network-based deblocking filters
US12556718B2 (en) * 2022-12-29 2026-02-17 Samsung Electronics Co., Ltd. Electronic device and method with image encoding and decoding
CN116805971B (zh) * 2023-04-11 2024-07-12 腾讯科技(深圳)有限公司 图像编解码方法、装置、设备
US12542932B2 (en) * 2023-04-12 2026-02-03 Qualcomm Incorporated Neural network-based in loop filter architectures with separable convolution and multi-scale enhancement for video coding
CN119211544A (zh) * 2023-06-26 2024-12-27 腾讯科技(深圳)有限公司 基于神经网络的图像滤波及编解码方法、装置、设备、存储介质
WO2025217290A1 (en) * 2024-04-10 2025-10-16 Qualcomm Incorporated Improvements of resnet based in-loop filter architecture for video coding

Family Cites Families (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11113800B2 (en) * 2017-01-18 2021-09-07 Nvidia Corporation Filtering image data using a neural network
EP3451293A1 (en) * 2017-08-28 2019-03-06 Thomson Licensing Method and apparatus for filtering with multi-branch deep learning
US10284432B1 (en) * 2018-07-03 2019-05-07 Kabushiki Kaisha Ubitus Method for enhancing quality of media transmitted via network
US11025907B2 (en) * 2019-02-28 2021-06-01 Google Llc Receptive-field-conforming convolution models for video coding
US10999606B2 (en) * 2019-01-08 2021-05-04 Intel Corporation Method and system of neural network loop filtering for video coding
US12282840B2 (en) 2019-01-11 2025-04-22 Samsung Electronics Co., Ltd. Method and apparatus with neural network layer contraction
KR102646695B1 (ko) 2019-01-15 2024-03-12 포틀랜드 스테이트 유니버시티 비디오 프레임 보간을 위한 특징 피라미드 워핑
EP3706046A1 (en) * 2019-03-04 2020-09-09 InterDigital VC Holdings, Inc. Method and device for picture encoding and decoding
EP3938962B1 (en) * 2019-03-15 2025-11-26 Dolby International AB Method and apparatus for updating a neural network
GB2620499B (en) 2019-03-20 2024-04-03 V Nova Int Ltd Low complexity enhancement video coding
KR20200114436A (ko) 2019-03-28 2020-10-07 국방과학연구소 스케일러블 영상 부호화를 수행하는 장치 및 방법
US10909728B1 (en) * 2019-05-01 2021-02-02 Amazon Technologies, Inc. Learned lossy image compression codec
US11216917B2 (en) 2019-05-03 2022-01-04 Amazon Technologies, Inc. Video enhancement using a neural network
US10944996B2 (en) 2019-08-19 2021-03-09 Intel Corporation Visual quality optimized video compression
US11647212B2 (en) 2020-09-30 2023-05-09 Qualcomm Incorporated Activation function design in neural network-based filtering process for video coding

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2025009938A1 (ko) * 2023-07-05 2025-01-09 엘지전자 주식회사 영상 부호화/복호화 방법, 비트스트림을 저장한 기록 매체 및 비트스트림을 전송하는 방법

Also Published As

Publication number Publication date
EP4222954A1 (en) 2023-08-09
JP2023543762A (ja) 2023-10-18
US11778213B2 (en) 2023-10-03
CN116325729B (zh) 2026-03-27
US20230012661A1 (en) 2023-01-19
PH12023550209A1 (en) 2024-06-24
WO2022072684A1 (en) 2022-04-07
US20220103845A1 (en) 2022-03-31
CN116325729A (zh) 2023-06-23
US11647212B2 (en) 2023-05-09
JP7787883B2 (ja) 2025-12-17

Similar Documents

Publication Publication Date Title
JP7795528B2 (ja) ビデオコーディング中にフィルタ処理するための複数のニューラルネットワークモデル
KR20230078653A (ko) 비디오 코딩을 위한 필터링 프로세스
US11778213B2 (en) Activation function design in neural network-based filtering process for video coding
KR20230081701A (ko) 비디오 코딩 동안 조인트-컴포넌트 뉴럴 네트워크 기반 필터링
KR20220008265A (ko) 비디오 코딩을 위한 제로-아웃 패턴들에 기초한 저 주파수 비 분리가능 변환 시그널링
KR20230038709A (ko) 다중 적응형 루프 필터 세트들
US20200288130A1 (en) Simplification of sub-block transforms in video coding
TW202118297A (zh) 用於視訊寫碼之縮放矩陣及傳訊
KR20230129015A (ko) 비디오 코딩 동안의 필터링을 위한 다수의 신경망 모델들
KR20230043101A (ko) 디블록킹 필터 파라미터 시그널링
US20200112728A1 (en) Wide-angle intra prediction for video coding
KR20230123947A (ko) 고정 필터들을 갖는 적응적 루프 필터
KR20230075443A (ko) 상이한 비트 심도에서 비디오 데이터의 코딩을 위한 적응적 루프 필터링의 동작 비트 심도의 제한
KR20230079049A (ko) 비디오 코딩에서의 크로스-컴포넌트 리니어 모델 (cclm) 모드에 대한 고정된 비트 심도 프로세싱
KR20230002323A (ko) 비디오 코딩을 위한 적응적 스케일링 리스트 제어
EP4035393A1 (en) Signaling number of sub-pictures in high-level syntax for video coding
KR20240159893A (ko) 비디오 코딩에서의 중첩 블록 모션 보상 (obmc) 블렌딩 선택
KR20250128971A (ko) 적응형 루프 필터 분류기들
KR20250034036A (ko) 비디오 코딩에서의 다수의 컬러 성분들에 대한 뉴럴 네트워크 기반 필터링 프로세스
KR20250034038A (ko) 비디오 데이터의 감소된 복잡도 다중 모드 뉴럴 네트워크 필터링
KR20250129641A (ko) 자연 비디오 콘텐츠를 위한 인트라 블록 카피
EP4674126A1 (en) Preprocessing of input data for adaptive loop filter in video coding

Legal Events

Date Code Title Description
PA0105 International application

Patent event date: 20230322

Patent event code: PA01051R01D

Comment text: International Patent Application

PG1501 Laying open of application
PA0201 Request for examination