TW202135529A - 使用基於循環的機器學習系統的視頻壓縮 - Google Patents

使用基於循環的機器學習系統的視頻壓縮 Download PDF

Info

Publication number
TW202135529A
TW202135529A TW110101726A TW110101726A TW202135529A TW 202135529 A TW202135529 A TW 202135529A TW 110101726 A TW110101726 A TW 110101726A TW 110101726 A TW110101726 A TW 110101726A TW 202135529 A TW202135529 A TW 202135529A
Authority
TW
Taiwan
Prior art keywords
time step
data
current time
video frame
reconstructed
Prior art date
Application number
TW110101726A
Other languages
English (en)
Chinese (zh)
Inventor
亞當 沃德馬 戈林斯基
楊洋
莎莉 瑞薩 普雷扎
古拉麥 康瑞德 索堤爾
羅森戴爾 泰斯 查漢 凡
塔可 賽巴斯汀 柯恩
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 TW202135529A publication Critical patent/TW202135529A/zh

Links

Images

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
    • H04N19/42—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by implementation details or hardware specially adapted for video compression or decompression, e.g. dedicated software implementation
    • H04N19/436—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by implementation details or hardware specially adapted for video compression or decompression, e.g. dedicated software implementation using parallelised computational arrangements
    • 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
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
    • 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
    • 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
    • G06N3/09—Supervised learning
    • 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
    • H04N19/136—Incoming video signal characteristics or properties
    • H04N19/137—Motion inside a coding unit, e.g. average field, frame or block difference
    • 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
    • H04N19/172—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 picture, frame or field
    • 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
    • H04N19/42—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by implementation details or hardware specially adapted for video compression or decompression, e.g. dedicated software implementation
    • 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
    • H04N19/50—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using predictive coding
    • H04N19/503—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using predictive coding involving temporal 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
    • H04N19/85—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using pre-processing or post-processing specially adapted for video compression

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Computing Systems (AREA)
  • Signal Processing (AREA)
  • Evolutionary Computation (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Biophysics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Software Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Image Analysis (AREA)
  • Processing Or Creating Images (AREA)
  • Compression Or Coding Systems Of Tv Signals (AREA)
  • Studio Devices (AREA)
TW110101726A 2020-03-03 2021-01-15 使用基於循環的機器學習系統的視頻壓縮 TW202135529A (zh)

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
US202062984673P 2020-03-03 2020-03-03
US62/984,673 2020-03-03
US17/091,570 2020-11-06
US17/091,570 US11405626B2 (en) 2020-03-03 2020-11-06 Video compression using recurrent-based machine learning systems

Publications (1)

Publication Number Publication Date
TW202135529A true TW202135529A (zh) 2021-09-16

Family

ID=77554929

Family Applications (1)

Application Number Title Priority Date Filing Date
TW110101726A TW202135529A (zh) 2020-03-03 2021-01-15 使用基於循環的機器學習系統的視頻壓縮

Country Status (9)

Country Link
US (1) US11405626B2 (enExample)
EP (1) EP4115617A1 (enExample)
JP (1) JP7628550B2 (enExample)
KR (1) KR20220150298A (enExample)
CN (1) CN115211115A (enExample)
BR (1) BR112022016793A2 (enExample)
PH (1) PH12022551821A1 (enExample)
TW (1) TW202135529A (enExample)
WO (1) WO2021178050A1 (enExample)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI824861B (zh) * 2022-11-30 2023-12-01 國立陽明交通大學 機器學習裝置及其訓練方法
TWI832406B (zh) * 2022-09-01 2024-02-11 國立陽明交通大學 反向傳播訓練方法和非暫態電腦可讀取媒體
TWI860054B (zh) * 2023-08-22 2024-10-21 國立清華大學 訓練機器學習模型的方法、裝置和電腦程式產品

Families Citing this family (43)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110677649B (zh) * 2019-10-16 2021-09-28 腾讯科技（深圳）有限公司 基于机器学习的去伪影方法、去伪影模型训练方法及装置
US12148120B2 (en) * 2019-12-18 2024-11-19 Ati Technologies Ulc Frame reprojection for virtual reality and augmented reality
WO2021220008A1 (en) 2020-04-29 2021-11-04 Deep Render Ltd Image compression and decoding, video compression and decoding: methods and systems
US11425402B2 (en) * 2020-07-20 2022-08-23 Meta Platforms, Inc. Cross-codec encoding optimizations for video transcoding
US11551090B2 (en) * 2020-08-28 2023-01-10 Alibaba Group Holding Limited System and method for compressing images for remote processing
US20220151540A1 (en) * 2020-11-19 2022-05-19 4N Inc. Explainable artificial intelligence system for diagnosis of mental diseases and the control method thereof
CN121771392A (zh) * 2020-12-17 2026-03-31 华为技术有限公司 基于神经网络的码流的解码和编码
CN116648906A (zh) * 2020-12-24 2023-08-25 华为技术有限公司 通过指示特征图数据进行编码
US11490078B2 (en) * 2020-12-29 2022-11-01 Tencent America LLC Method and apparatus for deep neural network based inter-frame prediction in video coding
US11570465B2 (en) * 2021-01-13 2023-01-31 WaveOne Inc. Machine-learned in-loop predictor for video compression
TWI804181B (zh) * 2021-02-02 2023-06-01 聯詠科技股份有限公司 影像編碼方法及其影像編碼器
US11399198B1 (en) * 2021-03-01 2022-07-26 Qualcomm Incorporated Learned B-frame compression
US11831909B2 (en) * 2021-03-11 2023-11-28 Qualcomm Incorporated Learned B-frame coding using P-frame coding system
US20240146938A1 (en) * 2021-03-18 2024-05-02 Nokia Technologies Oy Method, apparatus and computer program product for end-to-end learned predictive coding of media frames
WO2022221205A1 (en) 2021-04-13 2022-10-20 Headroom, Inc. Video super-resolution using deep neural networks
US20230019874A1 (en) * 2021-07-13 2023-01-19 Nintendo Co., Ltd. Systems and methods of neural network training
EP4420352A4 (en) * 2021-10-18 2025-09-03 Op Solutions Llc SYSTEMS AND METHODS FOR OPTIMIZING A LOSS FUNCTION FOR VIDEO CODING FOR MACHINES
US11546614B1 (en) * 2021-10-25 2023-01-03 Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V. Encoder and decoder for encoding and decoding images
CN116112673A (zh) * 2021-11-10 2023-05-12 华为技术有限公司 编解码方法及电子设备
WO2023092388A1 (zh) * 2021-11-25 2023-06-01 Oppo广东移动通信有限公司 解码方法、编码方法、解码器、编码器和编解码系统
US20230214630A1 (en) * 2021-12-30 2023-07-06 Cron Ai Ltd. (Uk) Convolutional neural network system, method for dynamically defining weights, and computer-implemented method thereof
WO2023138687A1 (en) * 2022-01-21 2023-07-27 Beijing Bytedance Network Technology Co., Ltd. Method, apparatus, and medium for data processing
US12548330B1 (en) 2022-01-26 2026-02-10 Upwork Inc. Determining engagement using sensor data
DE112022006625T5 (de) * 2022-02-08 2024-12-05 Nvidia Corporation Bilderzeugung unter verwendung eines neuronalen netzes
CN114545899B (zh) * 2022-02-10 2024-09-10 上海交通大学 基于先验知识的燃气轮机系统多传感器故障信号重构方法
US20230262237A1 (en) * 2022-02-15 2023-08-17 Adobe Inc. System and methods for video analysis
WO2023167502A1 (ko) * 2022-03-02 2023-09-07 엘지전자 주식회사 피쳐 부호화/복호화 방법, 장치, 비트스트림을 저장한 기록 매체 및 비트스트림 전송 방법
CN118872263A (zh) * 2022-03-03 2024-10-29 抖音视界有限公司 用于视觉数据处理的方法、装置和介质
CN115240099B (zh) * 2022-06-21 2026-04-03 有米科技股份有限公司 基于多模态关联数据的模型训练方法及装置
US20260067479A1 (en) * 2022-06-30 2026-03-05 Interdigital Ce Patent Holdings, Sas Fine-tuning a limited set of parameters in a deep coding system for images
WO2024015638A2 (en) * 2022-07-15 2024-01-18 Bytedance Inc. A neural network-based image and video compression method with conditional coding
CN119586135A (zh) * 2022-07-19 2025-03-07 字节跳动有限公司 具有可变率的基于神经网络的自适应图像和视频压缩方法
CN115604475B (zh) * 2022-08-12 2025-06-10 西安电子科技大学 一种多模态信源联合编码方法
WO2024054585A1 (en) 2022-09-09 2024-03-14 Tesla, Inc. Artificial intelligence modeling techniques for vision-based occupancy determination
KR20250086631A (ko) * 2022-09-30 2025-06-13 테슬라, 인크. 머신 러닝 모델들의 가속화된 비디오-기반 학습을 위한 시스템들 및 방법들
CN115294224B (zh) * 2022-09-30 2022-12-16 南通市通州区华凯机械有限公司 用于驾驶模拟器的图像数据快速载入方法
US20240169708A1 (en) * 2022-11-10 2024-05-23 Qualcomm Incorporated Processing video data using delta quantization
KR20240086085A (ko) * 2022-12-09 2024-06-18 삼성전자주식회사 시맨틱 맵에 기초하여 프레임 이미지를 복원하는 방법 및 장치
US12167003B2 (en) * 2023-02-19 2024-12-10 Deep Render Ltd. Method and data processing system for lossy image or video encoding, transmission, and decoding
WO2024175727A1 (en) * 2023-02-22 2024-08-29 Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V. Deep video coding with block-based motion estimation
WO2025198937A1 (en) * 2024-03-16 2025-09-25 Bytedance Inc. Method, apparatus, and medium for visual data processing
CN119922332A (zh) * 2025-01-21 2025-05-02 山东大学 一种基于隐式神经视频表示的视频编码方法及系统
CN121053039B (zh) * 2025-11-03 2026-01-27 北京铁力山科技股份有限公司 视频质量恢复方法、装置、设备及存储介质

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10192327B1 (en) * 2016-02-04 2019-01-29 Google Llc Image compression with recurrent neural networks
US10706351B2 (en) * 2016-08-30 2020-07-07 American Software Safety Reliability Company Recurrent encoder and decoder
CN109451308B (zh) 2018-11-29 2021-03-09 北京市商汤科技开发有限公司 视频压缩处理方法及装置、电子设备及存储介质

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI832406B (zh) * 2022-09-01 2024-02-11 國立陽明交通大學 反向傳播訓練方法和非暫態電腦可讀取媒體
TWI824861B (zh) * 2022-11-30 2023-12-01 國立陽明交通大學 機器學習裝置及其訓練方法
TWI860054B (zh) * 2023-08-22 2024-10-21 國立清華大學 訓練機器學習模型的方法、裝置和電腦程式產品

Also Published As

Publication number Publication date
JP7628550B2 (ja) 2025-02-10
PH12022551821A1 (en) 2024-02-12
JP2023517846A (ja) 2023-04-27
BR112022016793A2 (pt) 2022-10-11
KR20220150298A (ko) 2022-11-10
CN115211115A (zh) 2022-10-18
US11405626B2 (en) 2022-08-02
WO2021178050A1 (en) 2021-09-10
US20210281867A1 (en) 2021-09-09
EP4115617A1 (en) 2023-01-11

Similar Documents

Publication Publication Date Title
TW202135529A (zh) 使用基於循環的機器學習系統的視頻壓縮
US12003734B2 (en) Machine learning based flow determination for video coding
US12231666B2 (en) Front-end architecture for neural network based video coding
TWI883294B (zh) 用於基於神經網路的視訊譯碼的前端架構
CN116114247A (zh) 基于端到端神经网络的视频译码
TW202318878A (zh) 用於媒體變換譯碼的基於變換器的架構
TW202236849A (zh) 使用ｐ幀譯碼系統的學習ｂ幀譯碼
US11399198B1 (en) Learned B-frame compression
US12177473B2 (en) Video coding using optical flow and residual predictors
CN119923667A (zh) 基于扩散的数据压缩
US12394100B2 (en) Video coding using camera motion compensation and object motion compensation
WO2024137094A1 (en) Regularizing neural networks with data quantization using exponential family priors
JP7840973B2 (ja) ビデオコーディングのための機械学習ベースのフロー決定
TWI914390B (zh) 基於端到端神經網路的視訊譯碼
CN116965032A (zh) 用于视频译码的基于机器学习的流确定
CN116547965A (zh) 用于基于神经网络的视频译码的前端架构