JP7873680B2 - 機械学習システムを使用する暗黙的画像およびビデオ圧縮 - Google Patents

機械学習システムを使用する暗黙的画像およびビデオ圧縮

Info

Publication number
JP7873680B2
JP7873680B2 JP2023570426A JP2023570426A JP7873680B2 JP 7873680 B2 JP7873680 B2 JP 7873680B2 JP 2023570426 A JP2023570426 A JP 2023570426A JP 2023570426 A JP2023570426 A JP 2023570426A JP 7873680 B2 JP7873680 B2 JP 7873680B2
Authority
JP
Japan
Prior art keywords
model
image
neural network
weight values
bitstream
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
JP2023570426A
Other languages
English (en)
Japanese (ja)
Other versions
JP2024519791A (ja
JP2024519791A5 (cg-RX-API-DMAC7.html
Inventor
ジャン、インファン
バン・ロゼンダール、ティース・ジャン
コーエン、タコ・セバスティアーン
ナーゲル、マルクス
ブレーマー、ヨハン・ヒンリッヒ
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Qualcomm Inc
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 JP2024519791A publication Critical patent/JP2024519791A/ja
Publication of JP2024519791A5 publication Critical patent/JP2024519791A5/ja
Application granted granted Critical
Publication of JP7873680B2 publication Critical patent/JP7873680B2/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
    • H04N19/50—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
    • H04N19/51—Motion estimation or motion compensation
    • 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
    • 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
    • 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
    • H04N19/103—Selection of coding mode or of prediction 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
    • H04N19/124—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
    • H04N19/10—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
    • 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
    • H04N19/46—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
    • H04N19/51—Motion estimation or motion compensation
    • H04N19/537—Motion estimation other than block-based
    • 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
    • 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
    • H04N19/177—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 group of pictures [GOP]

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • General Physics & Mathematics (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Compression Or Coding Systems Of Tv Signals (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)
  • Compression, Expansion, Code Conversion, And Decoders (AREA)
  • Compression Of Band Width Or Redundancy In Fax (AREA)
JP2023570426A 2021-05-21 2022-03-31 機械学習システムを使用する暗黙的画像およびビデオ圧縮 Active JP7873680B2 (ja)

Applications Claiming Priority (5)

Application Number Priority Date Filing Date Title
US202163191606P 2021-05-21 2021-05-21
US63/191,606 2021-05-21
US17/645,018 US12206851B2 (en) 2021-05-21 2021-12-17 Implicit image and video compression using machine learning systems
US17/645,018 2021-12-17
PCT/US2022/022881 WO2022245434A1 (en) 2021-05-21 2022-03-31 Implicit image and video compression using machine learning systems

Publications (3)

Publication Number Publication Date
JP2024519791A JP2024519791A (ja) 2024-05-21
JP2024519791A5 JP2024519791A5 (cg-RX-API-DMAC7.html) 2025-03-10
JP7873680B2 true JP7873680B2 (ja) 2026-06-12

Family

ID=81392695

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2023570426A Active JP7873680B2 (ja) 2021-05-21 2022-03-31 機械学習システムを使用する暗黙的画像およびビデオ圧縮

Country Status (7)

Country Link
US (1) US12206851B2 (cg-RX-API-DMAC7.html)
EP (1) EP4342178A1 (cg-RX-API-DMAC7.html)
JP (1) JP7873680B2 (cg-RX-API-DMAC7.html)
KR (1) KR20240012374A (cg-RX-API-DMAC7.html)
BR (1) BR112023023427A2 (cg-RX-API-DMAC7.html)
TW (1) TW202247650A (cg-RX-API-DMAC7.html)
WO (1) WO2022245434A1 (cg-RX-API-DMAC7.html)

Families Citing this family (70)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11922314B1 (en) 2018-11-30 2024-03-05 Ansys, Inc. Systems and methods for building dynamic reduced order physical models
US11810225B2 (en) * 2021-03-30 2023-11-07 Zoox, Inc. Top-down scene generation
US11858514B2 (en) 2021-03-30 2024-01-02 Zoox, Inc. Top-down scene discrimination
US12159438B2 (en) * 2021-04-19 2024-12-03 Tencent America LLC Substitutional input optimization for adaptive neural image compression with smooth quality control
US12694572B2 (en) * 2021-06-16 2026-07-28 Google Llc Nonlinear peri-codec optimization for image and video coding
US12482256B2 (en) * 2021-06-22 2025-11-25 Electronics And Telecommunications Research Institute Method and apparatus for compression of a task output by machine learning
US20230013421A1 (en) * 2021-07-14 2023-01-19 Sony Group Corporation Point cloud compression using occupancy networks
KR20240089276A (ko) * 2021-10-06 2024-06-20 구글 엘엘씨 다중 언어 자동 스피치 인식을 위한 공동 비지도 및 지도 트레이닝
CN116348880B (zh) * 2021-10-21 2025-03-21 维萨国际服务协会 用于嵌入压缩和正则化的方法、系统和计算机程序产品
US20230196072A1 (en) * 2021-12-16 2023-06-22 Nokia Technologies Oy Iterative overfitting and freezing of decoder-side neural networks
MX2024007285A (es) * 2021-12-20 2024-08-20 Interdigital Vc Holdings Inc Redes neuronales basadas en atencion temporal para la comprension de video.
DE112022006625T5 (de) * 2022-02-08 2024-12-05 Nvidia Corporation Bilderzeugung unter verwendung eines neuronalen netzes
CN119096272A (zh) * 2022-04-28 2024-12-06 英迪股份有限公司 使用运动矢量场压缩的基于神经网络的视频压缩方法
US12354341B2 (en) * 2022-05-20 2025-07-08 Samsung Electronics Co., Ltd. Low-power change-based neural network inference for image processing
US11743552B1 (en) * 2022-06-03 2023-08-29 International Business Machines Corporation Computer technology for enhancing images with a generative adversarial network
US11689601B1 (en) * 2022-06-17 2023-06-27 International Business Machines Corporation Stream quality enhancement
KR20240081980A (ko) * 2022-12-01 2024-06-10 삼성전자주식회사 비디오 변환 방법 및 그 장치
EP4390774A1 (en) * 2022-12-21 2024-06-26 Fondation B-COM Method and device for decoding a bitstream
US12602834B2 (en) * 2022-12-27 2026-04-14 Tencent America LLC Long-range context model in neural image compression
US12556718B2 (en) * 2022-12-29 2026-02-17 Samsung Electronics Co., Ltd. Electronic device and method with image encoding and decoding
US12566627B2 (en) * 2023-01-20 2026-03-03 Dell Products L.P. Predicting the next best compressor in a stream data platform
US12499676B2 (en) * 2023-01-25 2025-12-16 Qualcomm Incorporated Recurrent neural networks for high resolution image and video processing
CN115834890B (zh) * 2023-02-08 2023-04-28 哈尔滨工业大学(深圳)(哈尔滨工业大学深圳科技创新研究院) 一种图像压缩方法、装置、设备及存储介质
US12542909B2 (en) * 2023-02-13 2026-02-03 Nec Corporation Analytics-aware video compression for decision making in teleoperated vehicle control
US12026924B1 (en) * 2023-02-19 2024-07-02 Deep Render Ltd. Method and data processing system for lossy image or video encoding, transmission and decoding
US12284364B2 (en) * 2023-03-06 2025-04-22 Sony Interactive Entertainment Inc. Machine learning (ML)-based rate control algorithm to find quantization parameter (QP)
CN118643872A (zh) * 2023-03-13 2024-09-13 北京字跳网络技术有限公司 一种模型量化方法、装置、电子设备及存储介质
CN116418990B (zh) * 2023-03-16 2026-06-30 北京工业大学 一种基于神经网络的用于压缩视频质量增强的方法
CN120937372A (zh) * 2023-03-20 2025-11-11 现代自动车株式会社 使用隐式神经表示模型的视频编码方法和设备
US12587663B2 (en) * 2023-03-22 2026-03-24 Qualcomm Incorporated Sliding-window rate-distortion optimization in neural network-based video coding
US12585816B2 (en) * 2023-03-27 2026-03-24 Ringcentral, Inc. Systems and methods for selective encryption of sensitive image data
KR102908814B1 (ko) 2023-04-10 2026-01-07 주식회사 딥엑스 Mpeg-vcm을 이용하여 추출된 특징맵을 송수신하는 장치 및 방법
CN116634162A (zh) * 2023-04-13 2023-08-22 南京大学 率失真优化的图像压缩神经网络训练后量化方法
CN116886922A (zh) * 2023-04-17 2023-10-13 中国科学院大学 视频处理方法、装置、电子设备及计算机可读存储介质
CN116227364B (zh) * 2023-04-25 2024-09-13 重庆大学 基于改进生成对抗网络与模型压缩的翼型流场预测方法
WO2024242387A1 (ko) * 2023-05-23 2024-11-28 현대자동차주식회사 암시적 신경망 표현에 기반하는 3d 비디오 코딩을 위한 방법 및 장치
FR3149158A1 (fr) 2023-05-24 2024-11-29 Orange Procédé et dispositif de codage et décodage d'images.
FR3151727A1 (fr) 2023-05-24 2025-01-31 Orange Procédé et dispositif de codage et décodage d'images.
US12573184B2 (en) 2023-05-30 2026-03-10 Acer Incorporated System and method for presenting three-dimensional content and three-dimensional content calculation apparatus
US12633095B2 (en) 2023-05-30 2026-05-19 Acer Incorporated Automatic efficient small model selection for monocular depth estimation
CN116994111B (zh) * 2023-05-31 2026-07-24 广东唯仁医疗科技有限公司 基于深度学习的oct共轭镜像去除方法及装置
GB2631452A (en) * 2023-06-30 2025-01-08 Sony Interactive Entertainment Deutschland Gmbh Neural coding and decoding method and apparatus
WO2025005519A1 (ko) * 2023-06-30 2025-01-02 현대자동차주식회사 암시적 신경망 표현 기반의 다중시점 비디오 코딩을 위한 방법 및 장치
CN116862019B (zh) * 2023-07-06 2024-03-19 清华大学 基于数据并行范式的模型训练方法及装置
CN121444431A (zh) * 2023-07-10 2026-01-30 交互数字Ce专利控股有限公司 使用隐式神经表示网络的视频压缩
WO2025011935A1 (en) * 2023-07-11 2025-01-16 Interdigital Ce Patent Holdings, Sas Approximating implicit neural representation through learnt dictionary atoms
US20250030856A1 (en) * 2023-07-20 2025-01-23 Sharp Kabushiki Kaisha Systems and methods for reducing distortion in end-to-end feature compression in coding of multi-dimensional data
CN119729047A (zh) * 2023-09-28 2025-03-28 北京字跳网络技术有限公司 视频处理方法、装置及电子设备
CN122029815A (zh) * 2023-10-12 2026-05-12 交互数字Ce专利控股有限公司 用于基于inr的视频压缩的具有引导式光流的渐进式扭曲层
US12634488B2 (en) * 2023-11-16 2026-05-19 Disney Enterprises, Inc. Tunable hybrid neural video representations
CN117541791B (zh) * 2023-11-23 2024-05-28 北京师范大学 基于多域可变形卷积的眼部结构分割方法、系统及设备
TWI860908B (zh) * 2023-12-05 2024-11-01 鴻海精密工業股份有限公司 全景環視模型構建方法、車載裝置及儲存介質
US12705460B2 (en) * 2023-12-12 2026-08-11 AtomBeam Technologies Inc. Systems and methods for perceptual quality-driven adaptive quantization in neural network data compression with dynamic feedback control
US12224777B1 (en) * 2023-12-12 2025-02-11 Atombeam Technologies Inc Systems and methods for neural network based data compression
CN117495741B (zh) * 2023-12-29 2024-04-12 成都货安计量技术中心有限公司 一种基于大卷积对比学习的畸变还原方法
WO2025153372A1 (en) * 2024-01-19 2025-07-24 Interdigital Ce Patent Holdings, Sas Efficient implementation of dictionary-based implicit neural representation
WO2025162700A1 (en) * 2024-01-30 2025-08-07 Interdigital Ce Patent Holdings, Sas Multi-definition implicit neural representation video encoding
WO2025168360A1 (en) * 2024-02-09 2025-08-14 Interdigital Ce Patent Holdings, Sas Multiscale dictionary learning and training of inr network
WO2025172429A1 (en) * 2024-02-15 2025-08-21 Deep Render Ltd Method and data processing system for lossy image or video encoding, transmission and decoding
GB202403951D0 (en) * 2024-03-20 2024-05-01 Deep Render Ltd Method and data processing system for lossy image or video encoding, transmission and decoding
EP4651481A1 (en) * 2024-05-14 2025-11-19 InterDigital CE Patent Holdings, SAS Shifting the parameters of a neural network based compression in decoding time
EP4697717A1 (en) * 2024-08-14 2026-02-18 InterDigital CE Patent Holdings, SAS Differential coding of implicit neural representation for video compression
FR3167809A1 (fr) 2024-10-21 2026-04-24 Orange Procédé et dispositif de codage et décodage d’images
US20260112135A1 (en) * 2024-10-22 2026-04-23 Interdigital Vc Holdings, Inc. Dynamic gaussian splatting learned from hierarchical motion model
EP4765812A1 (en) * 2024-12-19 2026-06-24 InterDigital CE Patent Holdings, SAS Pruning latent variable for hybrid implicit neural representation (inr)
EP4765810A1 (en) * 2024-12-19 2026-06-24 InterDigital CE Patent Holdings, SAS Pretrained auto regressive model (arm) for hybrid implicit neural representation (inr)
CN119922332B (zh) * 2025-01-21 2026-05-12 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
US20260220875A1 (en) * 2025-01-30 2026-07-30 Interdigital Vc Holdings, Inc. Gaussian splatting optimization with entropy constraints
KR102975052B1 (ko) * 2025-11-04 2026-06-08 서울과학기술대학교 산학협력단 Fpga 기반 완전 파이프라인 병목구조 및 배치처리를 이용한 고성능 경량신경망 추론 가속장치 및 그 동작방법
CN121309815B (zh) * 2025-12-12 2026-05-12 中电信人工智能科技(北京)有限公司 一种视频压缩传输方法和相关设备

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB201603144D0 (en) 2016-02-23 2016-04-06 Magic Pony Technology Ltd Training end-to-end video processes
US11196992B2 (en) 2015-09-03 2021-12-07 Mediatek Inc. Method and apparatus of neural network based processing in video coding
EP3451293A1 (en) 2017-08-28 2019-03-06 Thomson Licensing Method and apparatus for filtering with multi-branch deep learning
CN113748605A (zh) * 2019-03-18 2021-12-03 弗劳恩霍夫应用研究促进协会 用于压缩神经网络的参数的方法和装置
EP3716158A3 (en) * 2019-03-25 2020-11-25 Nokia Technologies Oy Compressing weight updates for decoder-side neural networks
US20220261616A1 (en) * 2019-07-02 2022-08-18 Vid Scale, Inc. Clustering-based quantization for neural network compression
EP4492337A3 (en) * 2019-09-11 2025-03-05 Naver Corporation Action recognition using implicit pose representations
EP4144087A1 (en) * 2020-04-29 2023-03-08 Deep Render Ltd Image compression and decoding, video compression and decoding: methods and systems
CN116134822A (zh) 2020-07-21 2023-05-16 交互数字Vc控股法国有限公司 用于更新基于深度神经网络的图像或视频解码器的方法和装置
WO2022139618A1 (en) * 2020-12-24 2022-06-30 Huawei Technologies Co., Ltd. Decoding with signaling of segmentation information

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
Adrian Kaehler, et al.,詳解 OpenCV 3,第1版,株式会社オライリー・ジャパン,2018年05月28日,p.817-821
Emilien Dupont, et.al.,COIN: COMPRESSION WITH IMPLICIT NEURAL REPRESENTATIONS,arXiv:2103.03123v2,2021年04月10日,pp.1-8,<URL:https://arxiv.org/abs/2103.03123>
Johannes Balle, et al.,VARIATIONAL IMAGE COMPRESSION WITH A SCALE HYPERPRIOR,arXiv:1802.01436v2,2018年05月01日,p.1-10,<URL:https://arxiv.org/abs/1802.01436>
Matthew Tancik, et al.,Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains,arXiv:2006.10739v1,2020年06月18日,p.1-2,<URL:https://arxiv.org/abs/2006.10739>

Also Published As

Publication number Publication date
JP2024519791A (ja) 2024-05-21
KR20240012374A (ko) 2024-01-29
TW202247650A (zh) 2022-12-01
EP4342178A1 (en) 2024-03-27
US12206851B2 (en) 2025-01-21
BR112023023427A2 (pt) 2024-01-30
US20220385907A1 (en) 2022-12-01
WO2022245434A1 (en) 2022-11-24

Legal Events

Date Code Title Description
A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20250228

A621 Written request for application examination

Free format text: JAPANESE INTERMEDIATE CODE: A621

Effective date: 20250228

A977 Report on retrieval

Free format text: JAPANESE INTERMEDIATE CODE: A971007

Effective date: 20251031

A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20251125

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: 20260512

A61 First payment of annual fees (during grant procedure)

Free format text: JAPANESE INTERMEDIATE CODE: A61

Effective date: 20260602

R150 Certificate of patent or registration of utility model

Ref document number: 7873680

Country of ref document: JP

Free format text: JAPANESE INTERMEDIATE CODE: R150