CN114747207B - 逐块神经图像压缩的方法和相关装置 - Google Patents

逐块神经图像压缩的方法和相关装置

Info

Publication number
CN114747207B
CN114747207B CN202180006196.3A CN202180006196A CN114747207B CN 114747207 B CN114747207 B CN 114747207B CN 202180006196 A CN202180006196 A CN 202180006196A CN 114747207 B CN114747207 B CN 114747207B
Authority
CN
China
Prior art keywords
block
prediction
reconstructed
region
generate
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.)
Active
Application number
CN202180006196.3A
Other languages
English (en)
Chinese (zh)
Other versions
CN114747207A (zh
Inventor
丁鼎
蒋薇
王炜
刘杉
许晓中
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.)
Tencent America LLC
Original Assignee
Tencent America LLC
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 Tencent America LLC filed Critical Tencent America LLC
Publication of CN114747207A publication Critical patent/CN114747207A/zh
Application granted granted Critical
Publication of CN114747207B publication Critical patent/CN114747207B/zh
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G06N3/0455—Auto-encoder networks; Encoder-decoder networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0464—Convolutional networks [CNN, ConvNet]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/09—Supervised learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00—Geometric image transformations in the plane of the image
    • G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
    • G06T3/4046—Scaling of whole images or parts thereof, e.g. expanding or contracting using neural networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T9/00—Image coding
    • G06T9/002—Image coding using neural networks
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
    • H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
    • H04N19/102—Methods 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
    • H04N19/103—Selection of coding mode or of prediction mode
    • H04N19/105—Selection of the reference unit for prediction within a chosen coding or prediction mode, e.g. adaptive choice of position and number of pixels used for prediction
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
    • H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
    • H04N19/102—Methods 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
    • H04N19/117—Filters, e.g. for pre-processing or post-processing
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
    • H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
    • H04N19/134—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or criterion affecting or controlling the adaptive coding
    • H04N19/157—Assigned coding mode, i.e. the coding mode being predefined or preselected to be further used for selection of another element or parameter
    • H04N19/159—Prediction type, e.g. intra-frame, inter-frame or bidirectional frame prediction
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
    • H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
    • H04N19/169—Methods 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
    • H04N19/17—Methods 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
    • H04N19/176—Methods 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
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
    • H04N19/50—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using predictive coding
    • H04N19/593—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using predictive coding involving spatial prediction techniques
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
    • H04N19/60—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using transform coding
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
    • H04N19/85—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using pre-processing or post-processing specially adapted for video compression
    • H04N19/86—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using pre-processing or post-processing specially adapted for video compression involving reduction of coding artifacts, e.g. of blockiness
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Linguistics (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (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)
CN202180006196.3A 2020-09-30 2021-08-27 逐块神经图像压缩的方法和相关装置 Active CN114747207B (zh)

Applications Claiming Priority (9)

Application Number Priority Date Filing Date Title
US202063085900P 2020-09-30 2020-09-30
US202063085908P 2020-09-30 2020-09-30
US63/085,900 2020-09-30
US63/085,908 2020-09-30
US202063088675P 2020-10-07 2020-10-07
US63/088,675 2020-10-07
US17/362,003 US12062150B2 (en) 2020-09-30 2021-06-29 Method and apparatus for block-wise neural image compression with post filtering
US17/362,003 2021-06-29
PCT/US2021/047996 WO2022072093A1 (en) 2020-09-30 2021-08-27 Method and apparatus for block-wise neural image compression with post filtering

Publications (2)

Publication Number Publication Date
CN114747207A CN114747207A (zh) 2022-07-12
CN114747207B true CN114747207B (zh) 2025-07-25

Family

ID=80822706

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202180006196.3A Active CN114747207B (zh) 2020-09-30 2021-08-27 逐块神经图像压缩的方法和相关装置

Country Status (6)

Country Link
US (1) US12062150B2 (cg-RX-API-DMAC7.html)
EP (1) EP4046375A4 (cg-RX-API-DMAC7.html)
JP (1) JP7520118B2 (cg-RX-API-DMAC7.html)
KR (1) KR102884426B1 (cg-RX-API-DMAC7.html)
CN (1) CN114747207B (cg-RX-API-DMAC7.html)
WO (1) WO2022072093A1 (cg-RX-API-DMAC7.html)

Families Citing this family (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN121078223A (zh) * 2019-11-08 2025-12-05 交互数字Ce专利控股有限公司 图像块的深度帧内预测
US12058312B2 (en) * 2021-10-06 2024-08-06 Kwai Inc. Generative adversarial network for video compression
US12518432B2 (en) * 2021-12-13 2026-01-06 Tencent America LLC System, method, and computer program for content adaptive online training for multiple blocks based on certain patterns
EP4470215A1 (en) * 2022-01-25 2024-12-04 InterDigital VC Holdings, Inc. Block-based compression and latent space intra prediction
WO2023198057A1 (en) * 2022-04-12 2023-10-19 Beijing Bytedance Network Technology Co., Ltd. Method, apparatus, and medium for video processing
WO2023225808A1 (en) * 2022-05-23 2023-11-30 Guangdong Oppo Mobile Telecommunications Corp., Ltd. Learned image compress ion and decompression using long and short attention module
CN117574994A (zh) * 2022-08-08 2024-02-20 华为技术有限公司 图像处理网络的训练、编解码方法及电子设备
CN119654864A (zh) * 2022-08-18 2025-03-18 三星电子株式会社 使用ai的图像解码设备和图像编码设备以及利用该设备的方法
CN117292237B (zh) * 2023-09-25 2024-08-20 深圳大学 基于局部Transformer网络的联合重构方法、装置及介质
US12652419B2 (en) 2023-11-06 2026-06-09 Samsung Electronics Co., Ltd. Apparatus and method for image encoding and decoding
CN122556068A (zh) * 2024-01-17 2026-08-11 字节跳动有限公司 媒体文件中采用jpeg ai编解码的定时图像序列的信令和存储
CN120008817B (zh) * 2025-01-21 2026-03-20 北京理工大学 一种基于神经网络的气体泄漏检测方法

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH05308629A (ja) 1992-05-01 1993-11-19 Olympus Optical Co Ltd 動画像符号化方式
JP3738511B2 (ja) 1997-01-20 2006-01-25 三菱電機株式会社 動画像符号化方式
US11196992B2 (en) * 2015-09-03 2021-12-07 Mediatek Inc. Method and apparatus of neural network based processing in video coding
JP6941943B2 (ja) 2017-02-01 2021-09-29 日本放送協会 予測装置およびプログラム
EP3451293A1 (en) * 2017-08-28 2019-03-06 Thomson Licensing Method and apparatus for filtering with multi-branch deep learning
EP4546785A3 (en) * 2017-10-13 2025-07-23 Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V. Intra-prediction mode concept for block-wise picture coding
WO2019093234A1 (ja) 2017-11-08 2019-05-16 パナソニック インテレクチュアル プロパティ コーポレーション オブ アメリカ 符号化装置、復号装置、符号化方法及び復号方法
US11228767B2 (en) * 2017-12-13 2022-01-18 Nokia Technologies Oy Apparatus, a method and a computer program for video coding and decoding
US11019355B2 (en) * 2018-04-03 2021-05-25 Electronics And Telecommunications Research Institute Inter-prediction method and apparatus using reference frame generated based on deep learning
JP7073186B2 (ja) 2018-05-14 2022-05-23 シャープ株式会社 画像フィルタ装置
CN110677644B (zh) * 2018-07-03 2021-11-16 北京大学 一种视频编码、解码方法及视频编码帧内预测器
CN111402237B (zh) * 2020-03-17 2023-04-18 山东大学 基于时空级联自编码器的视频图像异常检测方法及系统

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
DeepCoder: A deep neural network based video compression;Tong Chen等;2017 IEEE Visual Communications and Image Processing(VCIP),IEEE;20180228;1-4 *
Exploiting deep neural networks for digital image compression;Farhan Hussain等;2015 2nd World Symposium on Web Applications and Networking(WSWAN),IEEE;20150321;1-6 *

Also Published As

Publication number Publication date
EP4046375A4 (en) 2022-12-14
KR20220091606A (ko) 2022-06-30
JP2023504817A (ja) 2023-02-07
CN114747207A (zh) 2022-07-12
EP4046375A1 (en) 2022-08-24
WO2022072093A1 (en) 2022-04-07
KR102884426B1 (ko) 2025-11-13
US12062150B2 (en) 2024-08-13
JP7520118B2 (ja) 2024-07-22
US20220101492A1 (en) 2022-03-31

Similar Documents

Publication Publication Date Title
KR102884426B1 (ko) 사후 필터링에 의한 블록-단위 신경 이미지 압축을 위한 방법 및 장치
JP2023504817A5 (cg-RX-API-DMAC7.html)
KR102046521B1 (ko) 스킵 모드를 이용한 영상 복호화 방법 및 이러한 방법을 사용하는 장치
KR102173475B1 (ko) 픽처 예측 방법 및 픽처 예측 장치
KR20230010259A (ko) 사후-필터링을 위한 콘텐츠-적응형 온라인 트레이닝 방법 및 장치
RU2696304C2 (ru) Способ декодирования видеосигнала
JP7483030B2 (ja) 潜在特徴領域におけるイントラ予測によるニューラル画像圧縮
CN117793373A (zh) 机器学习视频处理系统和方法
KR102899660B1 (ko) 메타-학습에 의한 원활한 품질 제어가 있는 품질-적응 신경망-기반 루프 필터
WO2018119247A1 (en) Low-complexity sign prediction for video coding
CN114730475B (zh) 多尺度神经图像压缩方法、装置以及电子设备
JP7411113B2 (ja) 品質入力を有するループフィルタのためのマスクされたニューラルネットワークによるモデル共有
KR102749918B1 (ko) 품질-적응적 신경망-기반 루프 필터에 대한 치환 품질 인자 학습
CN116964632A (zh) 用于神经图像压缩中迭代内容自适应在线训练的系统、方法和计算机程序
JP6962193B2 (ja) 動画像符号化装置、動画像符号化方法および動画像符号化プログラムを記憶する記録媒体
CN115315956B (zh) 具有自适应帧内预测的神经网络图像压缩方法和装置
KR20140031974A (ko) 화상 부호화 방법, 화상 복호 방법, 화상 부호화 장치, 화상 복호 장치, 화상 부호화 프로그램 및 화상 복호 프로그램
JP7652925B2 (ja) ニューラル画像圧縮における複数ブロック用のコンテンツ適応型オンライン訓練のためのシステム、方法、およびコンピュータプログラム
JP7676578B2 (ja) ニューラルネットワークを使用する、エンドツーエンド(e2e)ニューラル画像圧縮(nic)用のコンテンツ適応型オンライン訓練の方法、装置及びコンピュータプログラム
CN118592029A (zh) 用于帧间预测的改进的局部照明补偿
JP5622613B2 (ja) 動画像符号化装置、動画像符号化方法及び動画像符号化プログラム
RU2777278C1 (ru) Способ и устройство для видеокодирования
CN119316619A (zh) 编解码方法和装置
HK40070661A (en) Multi-scale neural image compression method, apparatus and electronic device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant