TW202349967A - 用於基於神經的媒體壓縮的熵譯碼 - Google Patents

用於基於神經的媒體壓縮的熵譯碼 Download PDF

Info

Publication number
TW202349967A
TW202349967A TW112103265A TW112103265A TW202349967A TW 202349967 A TW202349967 A TW 202349967A TW 112103265 A TW112103265 A TW 112103265A TW 112103265 A TW112103265 A TW 112103265A TW 202349967 A TW202349967 A TW 202349967A
Authority
TW
Taiwan
Prior art keywords
data element
code vector
probability distribution
distribution function
media
Prior art date
Application number
TW112103265A
Other languages
English (en)
Chinese (zh)
Inventor
阿默 塞德
祝英浩
Original Assignee
美商高通公司
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 美商高通公司 filed Critical 美商高通公司
Publication of TW202349967A publication Critical patent/TW202349967A/zh

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
    • H04N19/90—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
    • H04N19/91—Entropy coding, e.g. variable length coding [VLC] or arithmetic coding
    • 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
    • G06N3/047—Probabilistic or stochastic 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
    • H04N19/124—Quantisation
    • 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
    • H04N19/46—Embedding additional information in the video signal during the compression process
    • H04N19/463—Embedding additional information in the video signal during the compression process by compressing encoding parameters before transmission
    • 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
    • H04N19/94—Vector quantisation

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • General Physics & Mathematics (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Probability & Statistics with Applications (AREA)
  • Compression Or Coding Systems Of Tv Signals (AREA)
  • Compression, Expansion, Code Conversion, And Decoders (AREA)
  • Image Analysis (AREA)
TW112103265A 2022-02-11 2023-01-31 用於基於神經的媒體壓縮的熵譯碼 TW202349967A (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US17/650,728 2022-02-11
US17/650,728 US12323634B2 (en) 2022-02-11 2022-02-11 Entropy coding for neural-based media compression

Publications (1)

Publication Number Publication Date
TW202349967A true TW202349967A (zh) 2023-12-16

Family

ID=85221768

Family Applications (1)

Application Number Title Priority Date Filing Date
TW112103265A TW202349967A (zh) 2022-02-11 2023-01-31 用於基於神經的媒體壓縮的熵譯碼

Country Status (7)

Country Link
US (1) US12323634B2 (enExample)
EP (1) EP4476913A1 (enExample)
JP (1) JP2025506100A (enExample)
KR (1) KR20240149890A (enExample)
CN (1) CN118872279A (enExample)
TW (1) TW202349967A (enExample)
WO (1) WO2023154590A1 (enExample)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP7665776B2 (ja) * 2021-03-26 2025-04-21 ドルビー ラボラトリーズ ライセンシング コーポレイション ニューラルネットワークを用いた画像及びビデオコーディングにおける潜時特徴の多分布エントロピーモデリング
EP4476914A1 (en) 2022-02-11 2024-12-18 Qualcomm Incorporated Neural-network media compression using quantized entropy coding distribution parameters
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
US12501050B2 (en) 2023-03-09 2025-12-16 Qualcomm Incorporated Efficient warping-based neural video codec
KR20250033760A (ko) * 2023-09-01 2025-03-10 삼성전자주식회사 최적화된 양자화 및 역양자화를 위한 영상 복호화 장치, 영상 복호화 방법, 영상 부호화 장치, 및 영상 부호화 방법
CN121168534B (zh) * 2025-11-19 2026-02-27 上海壁仞科技股份有限公司 基于对数量化的编解码方法和人工智能芯片

Family Cites Families (32)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP3413720B2 (ja) 1998-06-26 2003-06-09 ソニー株式会社 画像符号化方法及び装置、並びに画像復号方法及び装置
US6421467B1 (en) 1999-05-28 2002-07-16 Texas Tech University Adaptive vector quantization/quantizer
US7760911B2 (en) 2005-09-15 2010-07-20 Sarnoff Corporation Method and system for segment-based optical flow estimation
JP2010524383A (ja) 2007-04-09 2010-07-15 エルジー エレクトロニクス インコーポレイティド ビデオ信号処理方法及び装置
US8107550B2 (en) 2008-09-23 2012-01-31 Alcatel Lucent Methods for precoding signals for transmission in wireless MIMO system
WO2012122299A1 (en) 2011-03-07 2012-09-13 Xiph. Org. Bit allocation and partitioning in gain-shape vector quantization for audio coding
JP5845801B2 (ja) 2011-10-18 2016-01-20 ソニー株式会社 画像処理装置、画像処理方法、及び、プログラム
JP6315980B2 (ja) 2013-12-24 2018-04-25 株式会社東芝 デコーダ、デコード方法およびプログラム
US10075692B2 (en) 2015-01-28 2018-09-11 Hfi Innovation Inc. Method of simple intra mode for video coding
KR102251828B1 (ko) 2015-09-02 2021-05-13 삼성전자주식회사 율―왜곡 최적화 기반의 양자화 방법 및 그 장치
WO2018015963A1 (en) 2016-07-21 2018-01-25 Ramot At Tel-Aviv University Ltd. Method and system for comparing sequences
GB2586941B (en) 2017-08-01 2022-06-22 Displaylink Uk Ltd Reducing judder using motion vectors
KR102285064B1 (ko) 2017-10-30 2021-08-04 한국전자통신연구원 은닉 변수를 이용하는 영상 및 신경망 압축을 위한 방법 및 장치
US11257254B2 (en) * 2018-07-20 2022-02-22 Google Llc Data compression using conditional entropy models
US11109065B2 (en) 2018-09-26 2021-08-31 Google Llc Video encoding by providing geometric proxies
WO2020068498A1 (en) * 2018-09-27 2020-04-02 Google Llc Data compression using integer neural networks
US10652581B1 (en) * 2019-02-27 2020-05-12 Google Llc Entropy coding in image and video compression using machine learning
US20200356835A1 (en) 2019-05-09 2020-11-12 LGN Innovations Limited Sensor-Action Fusion System for Optimising Sensor Measurement Collection from Multiple Sensors
US11532155B1 (en) 2019-07-09 2022-12-20 ACME Atronomatic, LLC Methods and devices for earth remote sensing using stereoscopic hyperspectral imaging in the visible (VIS) and infrared (IR) bands
US11374952B1 (en) 2019-09-27 2022-06-28 Amazon Technologies, Inc. Detecting anomalous events using autoencoders
KR102287947B1 (ko) 2019-10-28 2021-08-09 삼성전자주식회사 영상의 ａｉ 부호화 및 ａｉ 복호화 방법, 및 장치
US11256967B2 (en) 2020-01-27 2022-02-22 Kla Corporation Characterization system and method with guided defect discovery
US11776679B2 (en) 2020-03-10 2023-10-03 The Board Of Trustees Of The Leland Stanford Junior University Methods for risk map prediction in AI-based MRI reconstruction
WO2022098737A1 (en) 2020-11-03 2022-05-12 Sri International Longitudinal datasets and machine learning models for menopause state and anomaly predictions
EP4250729A4 (en) 2021-02-22 2024-05-01 Samsung Electronics Co., Ltd. AI-BASED IMAGE ENCODING AND DECODING APPARATUS AND METHOD THEREFOR
EP4318376A4 (en) 2021-05-24 2024-05-22 Samsung Electronics Co., Ltd. Ai-based frame interpolation method and device
US20230185953A1 (en) 2021-12-14 2023-06-15 Sap Se Selecting differential privacy parameters in neural networks
US11599972B1 (en) 2021-12-22 2023-03-07 Deep Render Ltd. Method and system for lossy image or video encoding, transmission and decoding
US12307674B2 (en) 2022-02-03 2025-05-20 GE Precision Healthcare LLC Low latency interactive segmentation of medical images within a web-based deployment architecture
US11876969B2 (en) 2022-02-11 2024-01-16 Qualcomm Incorporated Neural-network media compression using quantized entropy coding distribution parameters
EP4476914A1 (en) * 2022-02-11 2024-12-18 Qualcomm Incorporated Neural-network media compression using quantized entropy coding distribution parameters
US11825090B1 (en) 2022-07-12 2023-11-21 Qualcomm Incorporated Bit-rate estimation for video coding with machine learning enhancement

Also Published As

Publication number Publication date
CN118872279A (zh) 2024-10-29
JP2025506100A (ja) 2025-03-07
US12323634B2 (en) 2025-06-03
US20230262267A1 (en) 2023-08-17
EP4476913A1 (en) 2024-12-18
KR20240149890A (ko) 2024-10-15
WO2023154590A1 (en) 2023-08-17

Similar Documents

Publication Publication Date Title
US11876969B2 (en) Neural-network media compression using quantized entropy coding distribution parameters
TW202349967A (zh) 用於基於神經的媒體壓縮的熵譯碼
TWI893191B (zh) 圖像編碼方法、圖像解碼方法及相關裝置
US12470715B2 (en) Neural-network media compression using quantized entropy coding distribution parameters
EP3938965A1 (en) An apparatus, a method and a computer program for training a neural network
WO2018058526A1 (zh) 视频编码方法、解码方法及终端
WO2022261838A1 (zh) 残差编码和视频编码方法、装置、设备和系统
WO2019114294A1 (zh) 图像编解码方法、装置、系统及存储介质
US10506258B2 (en) Coding video syntax elements using a context tree
WO2024196585A1 (en) Sliding-window rate-distortion optimization in neural network-based video coding
TW202337209A (zh) 編解碼方法、裝置、設備、儲存介質及電腦程式產品
CN119420903A (zh) 编解码方法、装置、发送比特流的方法、程序产品和介质
TW202446075A (zh) 高效的基於扭曲的神經視頻編解碼器
WO2023225854A1 (zh) 一种环路滤波方法、视频编解码方法、装置和系统
CN118633290A (zh) 使用量化熵编解码分布参数的神经网络媒体压缩
TW202349966A (zh) 濾波方法、濾波模型訓練方法及相關裝置
WO2018120290A1 (zh) 一种基于模板匹配的预测方法及装置
WO2025108861A1 (en) Differential quantization-constrained correction filter
CN121126003A (zh) 编解码方法、装置、设备、存储介质及程序产品
EP4627797A1 (en) Ai-based video conferencing using robust face restoration with adaptive quality control
CN120113243A (zh) 改进的熵旁路码处理