CN112785486A - 用于图像去噪声的自适应可变形核预测网络 - Google Patents

用于图像去噪声的自适应可变形核预测网络 Download PDF

Info

Publication number
CN112785486A
CN112785486A CN201911081492.0A CN201911081492A CN112785486A CN 112785486 A CN112785486 A CN 112785486A CN 201911081492 A CN201911081492 A CN 201911081492A CN 112785486 A CN112785486 A CN 112785486A
Authority
CN
China
Prior art keywords
graphics
pixel
memory
processor
data
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.)
Pending
Application number
CN201911081492.0A
Other languages
English (en)
Chinese (zh)
Inventor
姚安邦
陆鸣
王一凯
陈晓明
黄俊杰
吕涛
罗元轲
杨毅
陈�峰
王志明
郑治桥
王山东
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.)
Intel Corp
Original Assignee
Intel Corp
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 Intel Corp filed Critical Intel Corp
Priority to CN201911081492.0A priority Critical patent/CN112785486A/zh
Priority to JP2020150178A priority patent/JP2021077343A/ja
Priority to KR1020200124306A priority patent/KR20210055583A/ko
Priority to US17/090,170 priority patent/US11869171B2/en
Priority to DE102020129251.1A priority patent/DE102020129251A1/de
Publication of CN112785486A publication Critical patent/CN112785486A/zh
Priority to US18/514,252 priority patent/US20240127408A1/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T1/00—General purpose image data processing
    • G06T1/20—Processor architectures; Processor configuration, e.g. pipelining
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/70—Denoising; Smoothing
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/30—Arrangements for executing machine instructions, e.g. instruction decode
    • G06F9/38—Concurrent instruction execution, e.g. pipeline or look ahead
    • G06F9/3802—Instruction prefetching
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/30—Arrangements for executing machine instructions, e.g. instruction decode
    • G06F9/38—Concurrent instruction execution, e.g. pipeline or look ahead
    • G06F9/3802—Instruction prefetching
    • G06F9/3804—Instruction prefetching for branches, e.g. hedging, branch folding
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/30—Arrangements for executing machine instructions, e.g. instruction decode
    • G06F9/38—Concurrent instruction execution, e.g. pipeline or look ahead
    • G06F9/3885—Concurrent instruction execution, e.g. pipeline or look ahead using a plurality of independent parallel functional units
    • G06F9/3887—Concurrent instruction execution, e.g. pipeline or look ahead using a plurality of independent parallel functional units controlled by a single instruction for multiple data lanes [SIMD]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
    • G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
    • 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
    • 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
    • G06N3/045—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
    • G06N3/0464—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
    • G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
    • G06N3/063—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using electronic means
    • 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
    • G06N3/082—Learning methods modifying the architecture, e.g. adding, deleting or silencing nodes or connections
    • 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
    • G06T3/00—Geometric image transformations in the plane of the image
    • G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
    • G06T3/4046—Scaling of whole images or parts thereof, e.g. expanding or contracting using neural networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/60—Image enhancement or restoration using machine learning, e.g. neural 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
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20024—Filtering details
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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]

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • General Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Molecular Biology (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Linguistics (AREA)
  • Neurology (AREA)
  • Image Processing (AREA)
  • Image Generation (AREA)
  • Facsimile Image Signal Circuits (AREA)
CN201911081492.0A 2019-11-07 2019-11-07 用于图像去噪声的自适应可变形核预测网络 Pending CN112785486A (zh)

Priority Applications (6)

Application Number Priority Date Filing Date Title
CN201911081492.0A CN112785486A (zh) 2019-11-07 2019-11-07 用于图像去噪声的自适应可变形核预测网络
JP2020150178A JP2021077343A (ja) 2019-11-07 2020-09-07 画像のノイズ除去のための、適応型変形可能カーネル予測ネットワーク
KR1020200124306A KR20210055583A (ko) 2019-11-07 2020-09-24 이미지 노이즈 제거를 위한 적응형 디포머블 커널 예측 네트워크
US17/090,170 US11869171B2 (en) 2019-11-07 2020-11-05 Adaptive deformable kernel prediction network for image de-noising
DE102020129251.1A DE102020129251A1 (de) 2019-11-07 2020-11-06 Adaptives verformbares kernvorhersagenetzwerk zum bildentrauschen
US18/514,252 US20240127408A1 (en) 2019-11-07 2023-11-20 Adaptive deformable kernel prediction network for image de-noising

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911081492.0A CN112785486A (zh) 2019-11-07 2019-11-07 用于图像去噪声的自适应可变形核预测网络

Publications (1)

Publication Number Publication Date
CN112785486A true CN112785486A (zh) 2021-05-11

Family

ID=75584071

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911081492.0A Pending CN112785486A (zh) 2019-11-07 2019-11-07 用于图像去噪声的自适应可变形核预测网络

Country Status (5)

Country Link
US (2) US11869171B2 (enExample)
JP (1) JP2021077343A (enExample)
KR (1) KR20210055583A (enExample)
CN (1) CN112785486A (enExample)
DE (1) DE102020129251A1 (enExample)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113744156A (zh) * 2021-09-06 2021-12-03 中南大学 一种基于可变形卷积神经网络的图像去噪方法
CN113963009A (zh) * 2021-12-22 2022-01-21 中科视语(北京)科技有限公司 基于可形变划块的局部自注意力的图像处理方法和模型
CN115439340A (zh) * 2021-06-02 2022-12-06 辉达公司 用于图像处理的时空噪声掩模
CN115661784A (zh) * 2022-10-12 2023-01-31 北京惠朗时代科技有限公司 一种面向智慧交通的交通标志图像大数据识别方法与系统
CN115809964A (zh) * 2021-09-13 2023-03-17 三星电子株式会社 图像处理的方法和设备以及电子装置
US11869171B2 (en) 2019-11-07 2024-01-09 Intel Corporation Adaptive deformable kernel prediction network for image de-noising

Families Citing this family (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP4049236B1 (en) * 2019-11-14 2025-10-01 Huawei Technologies Co., Ltd. Spatially adaptive image filtering
US11418455B2 (en) 2020-08-31 2022-08-16 Micron Technology, Inc. Transparent packet splitting and recombining
US11296995B2 (en) 2020-08-31 2022-04-05 Micron Technology, Inc. Reduced sized encoding of packet length field
US11412075B2 (en) 2020-08-31 2022-08-09 Micron Technology, Inc. Multiple protocol header processing
US11360920B2 (en) * 2020-08-31 2022-06-14 Micron Technology, Inc. Mapping high-speed, point-to-point interface channels to packet virtual channels
US11539623B2 (en) 2020-08-31 2022-12-27 Micron Technology, Inc. Single field for encoding multiple elements
US11871145B2 (en) * 2021-04-06 2024-01-09 Adobe Inc. Optimization of adaptive convolutions for video frame interpolation
CN113516235B (zh) * 2021-07-13 2024-10-18 南京大学 一种可变形卷积加速器和可变形卷积加速方法
CN117561537A (zh) 2021-10-07 2024-02-13 三星电子株式会社 显示设备及其操作方法
US12462337B2 (en) * 2022-02-25 2025-11-04 Arm Limited System, devices and/or processes for processing image pixel values
CN114998964B (zh) * 2022-06-02 2023-04-18 天津道简智创信息科技有限公司 一种新型证照质量检测方法
GB2620920B (en) * 2022-07-21 2024-09-25 Advanced Risc Mach Ltd System, devices and/or processes for application of kernel coefficients
US12008728B2 (en) 2022-08-31 2024-06-11 Qualcomm Incorporated Apparatuses and methods for processing single instruction for image transformation from non-integral locations
CN116363480A (zh) * 2023-03-20 2023-06-30 南京大学 一种用于图像像素处理网络的计算装置和方法
CN119313587B (zh) * 2024-12-18 2025-03-28 浙江大华技术股份有限公司 基于块匹配的图像降噪方法、设备及存储介质

Family Cites Families (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7873812B1 (en) 2004-04-05 2011-01-18 Tibet MIMAR Method and system for efficient matrix multiplication in a SIMD processor architecture
US7747070B2 (en) * 2005-08-31 2010-06-29 Microsoft Corporation Training convolutional neural networks on graphics processing units
US10223333B2 (en) 2014-08-29 2019-03-05 Nvidia Corporation Performing multi-convolution operations in a parallel processing system
US10402700B2 (en) * 2016-01-25 2019-09-03 Deepmind Technologies Limited Generating images using neural networks
US10891538B2 (en) 2016-08-11 2021-01-12 Nvidia Corporation Sparse convolutional neural network accelerator
US10528864B2 (en) 2016-08-11 2020-01-07 Nvidia Corporation Sparse convolutional neural network accelerator
US11531852B2 (en) * 2016-11-28 2022-12-20 D-Wave Systems Inc. Machine learning systems and methods for training with noisy labels
US10475165B2 (en) * 2017-04-06 2019-11-12 Disney Enterprises, Inc. Kernel-predicting convolutional neural networks for denoising
US10607319B2 (en) * 2017-04-06 2020-03-31 Pixar Denoising monte carlo renderings using progressive neural networks
US10296578B1 (en) * 2018-02-20 2019-05-21 Paycor, Inc. Intelligent extraction and organization of data from unstructured documents
CN112785486A (zh) 2019-11-07 2021-05-11 英特尔公司 用于图像去噪声的自适应可变形核预测网络
WO2021147095A1 (en) * 2020-01-23 2021-07-29 Baidu.Com Times Technology (Beijing) Co., Ltd. Deep residual network for color filter array image denoising
EP4016446B1 (en) * 2020-12-21 2025-06-25 Dassault Systèmes Intelligent denoising
CN114693850A (zh) * 2020-12-25 2022-07-01 英特尔公司 用于图像和视频处理的条件核预测网络和自适应深度预测

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11869171B2 (en) 2019-11-07 2024-01-09 Intel Corporation Adaptive deformable kernel prediction network for image de-noising
CN115439340A (zh) * 2021-06-02 2022-12-06 辉达公司 用于图像处理的时空噪声掩模
CN113744156A (zh) * 2021-09-06 2021-12-03 中南大学 一种基于可变形卷积神经网络的图像去噪方法
CN115809964A (zh) * 2021-09-13 2023-03-17 三星电子株式会社 图像处理的方法和设备以及电子装置
CN113963009A (zh) * 2021-12-22 2022-01-21 中科视语(北京)科技有限公司 基于可形变划块的局部自注意力的图像处理方法和模型
CN115661784A (zh) * 2022-10-12 2023-01-31 北京惠朗时代科技有限公司 一种面向智慧交通的交通标志图像大数据识别方法与系统
CN115661784B (zh) * 2022-10-12 2023-08-22 北京惠朗时代科技有限公司 一种面向智慧交通的交通标志图像大数据识别方法与系统

Also Published As

Publication number Publication date
US20210142448A1 (en) 2021-05-13
US20240127408A1 (en) 2024-04-18
JP2021077343A (ja) 2021-05-20
DE102020129251A1 (de) 2021-05-12
KR20210055583A (ko) 2021-05-17
US11869171B2 (en) 2024-01-09

Similar Documents

Publication Publication Date Title
US20240127408A1 (en) Adaptive deformable kernel prediction network for image de-noising
US11145105B2 (en) Multi-tile graphics processor rendering
CN113366447A (zh) 图形处理中的计算优化
CN112534404A (zh) 用于矩阵加速器架构的稀疏优化
CN113424169A (zh) 用于临时缓冲的片上密集存储器
CN113383313A (zh) 用于图形处理的线程组调度
CN113837919A (zh) 用于基于着色速率来编码的方法和装置
CN114693850A (zh) 用于图像和视频处理的条件核预测网络和自适应深度预测
US20200293369A1 (en) Graphics systems and methods for accelerating synchronization using fine grain dependency check and scheduling optimizations based on available shared memory space
CN115526760A (zh) 用于动态地改变高速缓存中的数据优先级的方法和装置
CN113424219A (zh) 用于多线程通道的同步的系统和方法
CN112785482A (zh) 用于将可执行对象适配到处理单元的系统和方法
CN112785481A (zh) 动态分割激活和核以提高存储器效率
CN113256745A (zh) 用于基于重要度值来编码的方法和装置
CN113495793A (zh) 用于缓冲器共享的方法和装置
CN114677258A (zh) 用于视觉渲染和合成的空间稀疏卷积模块的方法和设备
CN113066042A (zh) 用于评估3d点云的质量的装置和方法
CN114693501A (zh) 用于图像处理的引导式神经网络模型的装置和方法
CN113424156A (zh) 用于利用队列和过渡存储以实现改善的低等待时间高带宽管芯上数据检取的系统和方法
CN113412475A (zh) 事务页错误处置
CN115511691A (zh) 像素流水线上的类型化乱序访问视图过载
CN114677259A (zh) 用于神经网络中的动态归一化和接力的方法和装置
CN115641250A (zh) 在图形处理单元的子核的私有高速缓存中执行全局存储器原子性
CN115526766A (zh) 用于基元的重叠像素的动态依赖关系记分牌
CN115794228A (zh) 用于点云处理的方法和装置

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination