BR112023005436A2 - Filtração baseada em rede neural de componente conjunto durante codificação de vídeo - Google Patents

Filtração baseada em rede neural de componente conjunto durante codificação de vídeo

Info

Publication number
BR112023005436A2
BR112023005436A2 BR112023005436A BR112023005436A BR112023005436A2 BR 112023005436 A2 BR112023005436 A2 BR 112023005436A2 BR 112023005436 A BR112023005436 A BR 112023005436A BR 112023005436 A BR112023005436 A BR 112023005436A BR 112023005436 A2 BR112023005436 A2 BR 112023005436A2
Authority
BR
Brazil
Prior art keywords
color component
neural network
filtered
size
component
Prior art date
Application number
BR112023005436A
Other languages
English (en)
Inventor
Chen Jianle
Wang Hongtao
Meher Satchit Anand KOTRA Venkata
Karczewicz Marta
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
Application filed by Qualcomm Inc filed Critical Qualcomm Inc
Publication of BR112023005436A2 publication Critical patent/BR112023005436A2/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
    • H04N19/169—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
    • H04N19/186—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 a colour or a chrominance component
    • 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
    • H04N19/80—Details of filtering operations specially adapted for video compression, e.g. for pixel interpolation
    • H04N19/82—Details of filtering operations specially adapted for video compression, e.g. for pixel interpolation involving filtering within a prediction loop
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/10—Interfaces, programming languages or software development kits, e.g. for simulating neural networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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
    • H04N19/117—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
    • H04N19/102—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
    • H04N19/132—Sampling, masking or truncation of coding units, e.g. adaptive resampling, frame skipping, frame interpolation or high-frequency transform coefficient masking
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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
    • G06N3/048—Activation functions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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]
    • 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
    • H04N19/90—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using coding techniques not provided for in groups H04N19/10-H04N19/85, e.g. fractals
    • H04N19/96—Tree coding, e.g. quad-tree coding

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Software Systems (AREA)
  • Computing Systems (AREA)
  • Artificial Intelligence (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Biophysics (AREA)
  • General Engineering & Computer Science (AREA)
  • Biomedical Technology (AREA)
  • Mathematical Physics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Compression Or Coding Systems Of Tv Signals (AREA)
  • Image Processing (AREA)

Abstract

FILTRAÇÃO BASEADA EM REDE NEURAL DE COMPONENTE CONJUNTO DURANTE CODIFICAÇÃO DE VÍDEO. Um dispositivo de exemplo para decodificar dados de vídeo inclui uma memória configurada para armazenar dados de vídeo; e um ou mais processadores implementados em conjunto de circuitos e configurados para: aplicar uma camada de rede neural de convolução de subamostragem a um primeiro componente de cor de um bloco de dados de vídeo, o primeiro componente de cor do bloco tendo um primeiro tamanho, em que a aplicação da camada de rede neural de convolução de subamostragem ao primeiro componente de cor gera um primeiro componente de cor subamostrado tendo um segundo tamanho menor do que o primeiro tamanho; filtrar um segundo componente de cor tendo o segundo tamanho para formar um segundo componente de cor filtrado; concatenar o primeiro componente de cor subamostrado com o segundo componente de cor filtrado para formar componentes de cor concatenados; e filtrar os componentes de cor concatenados para formar um componente concatenado filtrado incluindo um primeiro componente de cor subamostrado filtrado.
BR112023005436A 2020-10-05 2021-10-05 Filtração baseada em rede neural de componente conjunto durante codificação de vídeo BR112023005436A2 (pt)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US202063087784P 2020-10-05 2020-10-05
US17/493,543 US11825101B2 (en) 2020-10-05 2021-10-04 Joint-component neural network based filtering during video coding
PCT/US2021/053490 WO2022076355A1 (en) 2020-10-05 2021-10-05 Joint-component neural network based filtering during video coding

Publications (1)

Publication Number Publication Date
BR112023005436A2 true BR112023005436A2 (pt) 2023-05-09

Family

ID=80931851

Family Applications (1)

Application Number Title Priority Date Filing Date
BR112023005436A BR112023005436A2 (pt) 2020-10-05 2021-10-05 Filtração baseada em rede neural de componente conjunto durante codificação de vídeo

Country Status (7)

Country Link
US (1) US11825101B2 (pt)
EP (1) EP4226632A1 (pt)
JP (1) JP2023544705A (pt)
KR (1) KR20230081701A (pt)
CN (1) CN116508321A (pt)
BR (1) BR112023005436A2 (pt)
WO (1) WO2022076355A1 (pt)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP7030246B2 (ja) * 2019-06-25 2022-03-04 日本放送協会 イントラ予測装置、画像復号装置、及びプログラム
US20230186435A1 (en) * 2021-12-14 2023-06-15 Netflix, Inc. Techniques for component-based image preprocessing
WO2023198057A1 (en) * 2022-04-12 2023-10-19 Beijing Bytedance Network Technology Co., Ltd. Method, apparatus, and medium for video processing
WO2024010710A1 (en) * 2022-07-04 2024-01-11 Dolby Laboratories Licensing Corporation Loop filtering using neural networks
KR20240019638A (ko) * 2022-08-04 2024-02-14 삼성전자주식회사 크로마 성분 예측을 수행하는 ai에 기반한 비디오 복호화 장치 및 방법, 및 비디오 부호화 장치 및 방법

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2020047536A1 (en) * 2018-08-31 2020-03-05 Board Of Regents, University Of Texas System Deep learning based dosed prediction for treatment planning and quality assurance in radiation therapy
EP3706046A1 (en) 2019-03-04 2020-09-09 InterDigital VC Holdings, Inc. Method and device for picture encoding and decoding

Also Published As

Publication number Publication date
EP4226632A1 (en) 2023-08-16
WO2022076355A1 (en) 2022-04-14
KR20230081701A (ko) 2023-06-07
US20220109860A1 (en) 2022-04-07
JP2023544705A (ja) 2023-10-25
CN116508321A (zh) 2023-07-28
US11825101B2 (en) 2023-11-21

Similar Documents

Publication Publication Date Title
BR112023005436A2 (pt) Filtração baseada em rede neural de componente conjunto durante codificação de vídeo
BR112023004814A2 (pt) Múltiplos modelos de rede neural para filtragem durante a codificação de vídeo
BR112019002896A2 (pt) codificação intravídeo usando uma estrutura do tipo árvore desacoplada
BR112015006479A2 (pt) definição de unidade de decodificação expandida
BR112022004883A2 (pt) Método implementado por um decodificador, mídia legível por computador não transitória, e dispositivo de decodificação
BR112021018855A2 (pt) Seleção de multitransformadas estendida para codificação de vídeo
BR112018077294A2 (pt) sistemas e métodos para identificação de conteúdo correspondente
BR112017022248A2 (pt) ajuste de faixa dinâmica para faixa dinâmica alta e conversão de vídeo em código de gama de cores ampla
BR112016029691A2 (pt) projeto extensível de mensagens da informação suplementar do realce (sei) de aninhamento
BR112018068873A2 (pt) método e dispositivo para codificar uma imagem de alta faixa dinâmica, método de decodificação correspondente e dispositivo de decodificação
BR112023004483A2 (pt) Processo de filtragem para codificação de vídeo
BR112022022058A2 (pt) Elementos de sintaxe de conjunto de parâmetros e variáveis em codificação de vídeo
BR112023003932A2 (pt) Codificação de vídeo baseada em rede neural de ponta a ponta
BR112021023252A2 (pt) Codificação de coeficiente para modo de pulo de transformada em codificação de vídeo
BR112022016463A2 (pt) Codificação e decodificação de vídeo
BR112022016976A2 (pt) Sinalização de subimagem na codificação de vídeo
BR112022019193A2 (pt) Particionamento de bloco para codificação de imagem e vídeo
BR112017015593A2 (pt) método e aparelho de codificação e decodificação de uma imagem a cores
BRPI0804965A2 (pt) método para tratar cabelo
Tang “It is not a something, but not a nothing either!”—McDowell on Wittgenstein
Su-yeon An Examination of the Effect Enhanced Comprehension of Sex Related Stories Has on Preventing SEXUAL VIOLENCE for Children of Age Five
de Groot Latin-American European citizens: Some consequences of the autonomy of the member States of the European Union in nationality matters
Zhang Effect of Glucagon‐Like Peptide‐1 Receptor Agonist (GLP1RA) on Hypertension‐Induced Atrial Remodelling
Costa et al. Being psychologically abused is not enough into ending a relationship: Sunk cost effect in intimate abusive relationships
Kellogg St. Augustine and the Parson's Tale