BR112023013954A2 - Compressão progressiva de dados usando redes neurais artificiais - Google Patents

Compressão progressiva de dados usando redes neurais artificiais

Info

Publication number
BR112023013954A2
BR112023013954A2 BR112023013954A BR112023013954A BR112023013954A2 BR 112023013954 A2 BR112023013954 A2 BR 112023013954A2 BR 112023013954 A BR112023013954 A BR 112023013954A BR 112023013954 A BR112023013954 A BR 112023013954A BR 112023013954 A2 BR112023013954 A2 BR 112023013954A2
Authority
BR
Brazil
Prior art keywords
content
compressed version
encoded
artificial neural
quantization bin
Prior art date
Application number
BR112023013954A
Other languages
English (en)
Portuguese (pt)
Inventor
Amir Said
Sebastiaan Cohen Taco
Yadong Lu
Yang Yang
Yinhao Zhu
Original Assignee
Qualcomm Inc
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 Qualcomm Inc filed Critical Qualcomm Inc
Publication of BR112023013954A2 publication Critical patent/BR112023013954A2/pt

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
    • 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
    • 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
    • H03M7/3082—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)
BR112023013954A 2021-01-25 2022-01-25 Compressão progressiva de dados usando redes neurais artificiais BR112023013954A2 (pt)

Applications Claiming Priority (3)

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

Publications (1)

Publication Number Publication Date
BR112023013954A2 true BR112023013954A2 (pt) 2023-11-07

Family

ID=80284798

Family Applications (1)

Application Number Title Priority Date Filing Date
BR112023013954A BR112023013954A2 (pt) 2021-01-25 2022-01-25 Compressão progressiva de dados usando redes neurais artificiais

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

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11562208B2 (en) 2018-05-17 2023-01-24 Qualcomm Incorporated Continuous relaxation of quantization for discretized deep neural networks
US11257254B2 (en) 2018-07-20 2022-02-22 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
US10886943B2 (en) * 2019-03-18 2021-01-05 Samsung Electronics Co., Ltd Method and apparatus for variable rate compression with a conditional autoencoder

Also Published As

Publication number Publication date
EP4282076A1 (en) 2023-11-29
KR20230136121A (ko) 2023-09-26
JP2024504315A (ja) 2024-01-31
JP7850166B2 (ja) 2026-04-22
WO2022159897A1 (en) 2022-07-28

Similar Documents

Publication Publication Date Title
BR112023013954A2 (pt) Compressão progressiva de dados usando redes neurais artificiais
PH12019550191A1 (en) Neural network processor using compression and decompression of activation data to reduce memory bandwidth utilization
US10735025B2 (en) Use of data prefixes to increase compression ratios
MX2021002284A (es) Relacion entre elementos de restriccion de particion.
BR112021024812A2 (pt) Modelagem de contexto para sinalização de transformação não separável de baixa frequência para codificação de vídeo
EP4535240A3 (en) Data compression using conditional entropy models
BR112018007808A2 (pt) método para compressão de dados, mídia legível por computador, sistema para compressão de dados, método para comprimir dados de pelo menos uma unidade de sensor, montagem de iluminação e rede de comunicação
MX2023010006A (es) Metodo y aparato de codificacion de datos de imagen y metodo y aparato de decodificacion de datos de imagen.
MY204413A (en) Method and apparatus for storing data, and computer device and storage medium thereof
KR20200105432A (ko) 데이터를 압축하기 위한 방법들 및 장치들
BR112018073902A2 (pt) sinalização de vídeo de realidade virtual em transmissão contínua adaptativa dinâmica através de http
BR112022025890A2 (pt) Ajuste de campo sonoro
BR112021017451A2 (pt) Seleção de transformada implícita em codificação de vídeo
BR112023026161A2 (pt) Extração de recurso de canal através de redes neurais baseadas em modelo
ZA202110269B (en) Clipping indices coding for adaptive loop filter in video coding
BR112015025478A2 (pt) métodos e aparelhos de codificação e de decodificação de dados, dados de imagem codificados, portador de dados, software de computador, meio de armazenamento legível por máquina, e, aparelho de armazenamento e/ou exibição, transmissão, captura de dados de vídeo
PH12019500783A1 (en) Methods and devices for encoding and decoding binary data
IL294187A (en) Methods and systems for information compression
RU2013144665A (ru) Кодер, способ кодирования данных, декодер, способ декодирования данных, система передачи данных, способ передачи данных и программный продукт
BR112023004496A2 (pt) Quantização dinâmica para aprendizado profundo com eficiencia energética
BR112019002888A2 (pt) método e aparelho de transmissão de dados por definir limiares de segmentação com base no intervalo de tempo de transmissão
BR112023017266A2 (pt) Técnicas de codificação para arquiteturas de rede neural
BR112022000094A2 (pt) Codificador, decodificador, métodos e fluxo de dados
EP4535791A3 (en) Image coding method based on transform, and device therefor
BR112022005290A2 (pt) Método e aparelho para sinalização de parâmetros de quantização de crominância