JP7850166B2 - 人工ニューラルネットワークを使用する逐次データ圧縮 - Google Patents

人工ニューラルネットワークを使用する逐次データ圧縮

Info

Publication number
JP7850166B2
JP7850166B2 JP2023543424A JP2023543424A JP7850166B2 JP 7850166 B2 JP7850166 B2 JP 7850166B2 JP 2023543424 A JP2023543424 A JP 2023543424A JP 2023543424 A JP2023543424 A JP 2023543424A JP 7850166 B2 JP7850166 B2 JP 7850166B2
Authority
JP
Japan
Prior art keywords
quantization
quantization bin
content
encoded
compression
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
JP2023543424A
Other languages
English (en)
Japanese (ja)
Other versions
JP2024504315A (ja
JP2024504315A5 (https=
Inventor
ヤドン・ル
ヤン・ヤン
インハオ・ジュ
アミール・サイド
タコ・セバスティアーン・コーヘン
Original Assignee
クアルコム，インコーポレイテッド
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 US17/648,808 external-priority patent/US12008731B2/en
Application filed by クアルコム，インコーポレイテッド filed Critical クアルコム，インコーポレイテッド
Publication of JP2024504315A publication Critical patent/JP2024504315A/ja
Publication of JP2024504315A5 publication Critical patent/JP2024504315A5/ja
Application granted granted Critical
Publication of JP7850166B2 publication Critical patent/JP7850166B2/ja
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • 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
    • H04N19/124—Quantisation
    • 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
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0495—Quantised networks; Sparse networks; Compressed 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
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • 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
    • G06N3/088—Non-supervised learning, e.g. competitive learning
    • H—ELECTRICITY
    • H03—ELECTRONIC CIRCUITRY
    • H03M—CODING; DECODING; CODE CONVERSION IN GENERAL
    • H03M7/00—Conversion of a code where information is represented by a given sequence or number of digits to a code where the same, similar or subset of information is represented by a different sequence or number of digits
    • H03M7/30—Compression; Expansion; Suppression of unnecessary data, e.g. redundancy reduction
    • H03M7/3059—Digital compression and data reduction techniques where the original information is represented by a subset or similar information, e.g. lossy compression
    • H—ELECTRICITY
    • H03—ELECTRONIC CIRCUITRY
    • H03M—CODING; DECODING; CODE CONVERSION IN GENERAL
    • H03M7/00—Conversion of a code where information is represented by a given sequence or number of digits to a code where the same, similar or subset of information is represented by a different sequence or number of digits
    • H03M7/30—Compression; Expansion; Suppression of unnecessary data, e.g. redundancy reduction
    • H03M7/3082—Vector 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
    • H04N19/10—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
    • H04N19/112—Selection of coding mode or of prediction mode according to a given display mode, e.g. for interlaced or progressive display mode
    • 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
    • H04N19/119—Adaptive subdivision aspects, e.g. subdivision of a picture into rectangular or non-rectangular coding blocks
    • 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
    • H04N19/124—Quantisation
    • H04N19/126—Details of normalisation or weighting functions, e.g. normalisation matrices or variable uniform quantisers
    • 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
    • H04N19/146—Data rate or code amount at the encoder output
    • 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
    • H04N19/146—Data rate or code amount at the encoder output
    • H04N19/147—Data rate or code amount at the encoder output according to rate distortion criteria

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Molecular Biology (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Compression Or Coding Systems Of Tv Signals (AREA)
  • Compression, Expansion, Code Conversion, And Decoders (AREA)
JP2023543424A 2021-01-25 2022-01-25 人工ニューラルネットワークを使用する逐次データ圧縮 Active JP7850166B2 (ja)

Applications Claiming Priority (5)

Application Number Priority Date Filing Date Title
US202163141322P 2021-01-25 2021-01-25
US63/141,322 2021-01-25
US17/648,808 US12008731B2 (en) 2021-01-25 2022-01-24 Progressive data compression using artificial neural networks
US17/648,808 2022-01-24
PCT/US2022/013723 WO2022159897A1 (en) 2021-01-25 2022-01-25 Progressive data compression using artificial neural networks

Publications (3)

Publication Number Publication Date
JP2024504315A JP2024504315A (ja) 2024-01-31
JP2024504315A5 JP2024504315A5 (https=) 2025-01-10
JP7850166B2 true JP7850166B2 (ja) 2026-04-22

Family

ID=80284798

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2023543424A Active JP7850166B2 (ja) 2021-01-25 2022-01-25 人工ニューラルネットワークを使用する逐次データ圧縮

Country Status (5)

Country Link
EP (1) EP4282076A1 (https=)
JP (1) JP7850166B2 (https=)
KR (1) KR20230136121A (https=)
BR (1) BR112023013954A2 (https=)
WO (1) WO2022159897A1 (https=)

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114827622A (zh) 2021-01-19 2022-07-29 华为技术有限公司 分层编解码的方法及装置
CN116778002A (zh) * 2022-03-10 2023-09-19 华为技术有限公司 编解码方法、装置、设备、存储介质及计算机程序产品
CN119815080B (zh) * 2022-07-14 2025-12-26 杭州海康威视数字技术股份有限公司 一种基于神经网络的图像解码、编码方法、装置及其设备
CN120323013A (zh) * 2022-12-05 2025-07-15 抖音视界有限公司 用于经学习的压缩模型的从熵量化角度的可控可变率
CN116260969B (zh) * 2023-05-15 2023-08-18 鹏城实验室 一种自适应的通道渐进式编解码方法、装置、终端及介质
EP4728734A1 (en) * 2023-06-14 2026-04-22 Dolby Laboratories Licensing Corporation Error protection for neural field streaming
US20260046460A1 (en) * 2024-08-09 2026-02-12 Synaptics Incorporated Progressive coding for autoencoders
CN119383348B (zh) * 2024-10-11 2025-10-28 西安电子科技大学 基于分布式的感兴趣区域图像压缩方法

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190354842A1 (en) 2018-05-17 2019-11-21 Qualcomm Incorporated Continuous relaxation of quantization for discretized deep neural networks
US20200027247A1 (en) 2018-07-20 2020-01-23 Google Llc Data compression using conditional entropy models
US20200160565A1 (en) 2018-11-19 2020-05-21 Zhan Ma Methods And Apparatuses For Learned Image Compression
US20200304147A1 (en) 2019-03-18 2020-09-24 Samsung Electronics Co., Ltd. Method and apparatus for variable rate compression with a conditional autoencoder

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190354842A1 (en) 2018-05-17 2019-11-21 Qualcomm Incorporated Continuous relaxation of quantization for discretized deep neural networks
US20200027247A1 (en) 2018-07-20 2020-01-23 Google Llc Data compression using conditional entropy models
US20200160565A1 (en) 2018-11-19 2020-05-21 Zhan Ma Methods And Apparatuses For Learned Image Compression
US20200304147A1 (en) 2019-03-18 2020-09-24 Samsung Electronics Co., Ltd. Method and apparatus for variable rate compression with a conditional autoencoder

Non-Patent Citations (5)

* Cited by examiner, † Cited by third party
Title
David Minnen, Johannes Balle, and George Toderici，Joint autoregressive and hierarchical priors for learned image compression，NIPS'18: Proceedings of the 32nd International Conference on Neural Information Processing Systems，ACM，2018年12月，pp.1-10，https://dl.acm.org/doi/10.5555/3327546.3327736
Jing Zhou, et al.，Variable Rate Image Compression Method with Dead-zone Quantizer，2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)，IEEE，2020年，pp.624-628
Mohammad Akbari, Jie Liang, Jingning Hany, and Chengjie Tu，LEARNED VARIABLE-RATE IMAGE COMPRESSION WITH RESIDUAL DIVISIVE NORMALIZATION，arXiv:1912.05688v1，arXiv，2019年12月11日，pp.1-6
Yadong Lu, et al.，PROGRESSIVE NEURAL IMAGE COMPRESSION WITH NESTED QUANTIZATION AND LATENT ORDERING，arXiv:2102.02913v1，arXiv，2021年02月04日，pp.1-7
Yoojin Choi, Mostafa El-Khamy, and Jungwon Lee，Variable Rate Deep Image CompressionWith a Conditional Autoencoder，2019 IEEE/CVF International Conference on Computer Vision (ICCV)，IEEE，2020年，pp.3146-3154

Also Published As

Publication number Publication date
EP4282076A1 (en) 2023-11-29
KR20230136121A (ko) 2023-09-26
JP2024504315A (ja) 2024-01-31
BR112023013954A2 (pt) 2023-11-07
WO2022159897A1 (en) 2022-07-28

Similar Documents

Publication Publication Date Title
JP7850166B2 (ja) 人工ニューラルネットワークを使用する逐次データ圧縮
US12008731B2 (en) Progressive data compression using artificial neural networks
US11423310B2 (en) Deep learning based adaptive arithmetic coding and codelength regularization
US11616988B2 (en) Method and device for evaluating subjective quality of video
KR102285738B1 (ko) 영상의 주관적 품질을 평가하는 방법 및 장치
KR102287947B1 (ko) 영상의 ａｉ 부호화 및 ａｉ 복호화 방법, 및 장치
JP2022529580A (ja) ビデオ符号化における残差の処理
CN111868753A (zh) 使用条件熵模型的数据压缩
US20230230288A1 (en) Image compression and decoding, video compression and decoding: training methods and training systems
WO2022122965A1 (en) Method and data processing system for lossy image or video encoding, transmission and decoding
WO2023118317A1 (en) Method and data processing system for lossy image or video encoding, transmission and decoding
CN112715029B (zh) Ai编码设备及其操作方法和ai解码设备及其操作方法
Fu et al. Improved hybrid layered image compression using deep learning and traditional codecs
US20230316588A1 (en) Online training-based encoder tuning with multi model selection in neural image compression
KR20210056179A (ko) Ai 부호화 장치 및 그 동작방법, 및 ai 복호화 장치 및 그 동작방법
US12418668B2 (en) Alias-free compression of content using artificial neural networks
CN116746066A (zh) 使用人工神经网络的渐进式数据压缩
EP4701180A1 (en) Data processing method using neural network model and electronic device for performing the same
EP4700653A1 (en) Method of processing data using neural network model and electronic device for performing the same
EP4693196A1 (en) Progressive coding for autoencoders
Mehrotra Adaptive VQ with Memory and Hierarchical Table Lookups EE391

Legal Events

Date Code Title Description
A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20241226

A621 Written request for application examination

Free format text: JAPANESE INTERMEDIATE CODE: A621

Effective date: 20241226

A977 Report on retrieval

Free format text: JAPANESE INTERMEDIATE CODE: A971007

Effective date: 20251024

A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20251104

A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20260203

TRDD Decision of grant or rejection written
A01 Written decision to grant a patent or to grant a registration (utility model)

Free format text: JAPANESE INTERMEDIATE CODE: A01

Effective date: 20260317

A61 First payment of annual fees (during grant procedure)

Free format text: JAPANESE INTERMEDIATE CODE: A61

Effective date: 20260410

R150 Certificate of patent or registration of utility model

Ref document number: 7850166

Country of ref document: JP

Free format text: JAPANESE INTERMEDIATE CODE: R150