BR112022022218A2 - Ajuste de imagem com base em aprendizado de máquina - Google Patents

Ajuste de imagem com base em aprendizado de máquina

Info

Publication number
BR112022022218A2
BR112022022218A2 BR112022022218A BR112022022218A BR112022022218A2 BR 112022022218 A2 BR112022022218 A2 BR 112022022218A2 BR 112022022218 A BR112022022218 A BR 112022022218A BR 112022022218 A BR112022022218 A BR 112022022218A BR 112022022218 A2 BR112022022218 A2 BR 112022022218A2
Authority
BR
Brazil
Prior art keywords
image
machine learning
maps
image data
generate
Prior art date
Application number
BR112022022218A
Other languages
English (en)
Portuguese (pt)
Inventor
Dangi Shusil
Hwang Hau
Ravi Kiran Dayana Venkata
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 BR112022022218A2 publication Critical patent/BR112022022218A2/pt

Links

Classifications

    • 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
    • G06N3/04—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
    • G06N3/08—Learning methods
    • G06N3/09—Supervised learning
    • 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
    • G06T5/60—Image enhancement or restoration using machine learning, e.g. neural networks
    • 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
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/73—Deblurring; Sharpening
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/90—Dynamic range modification of images or parts thereof
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/80—Camera processing pipelines; Components thereof
    • H04N23/84—Camera processing pipelines; Components thereof for processing colour signals
    • H04N23/88—Camera processing pipelines; Components thereof for processing colour signals for colour balance, e.g. white-balance circuits or colour temperature control
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N9/00—Details of colour television systems
    • H04N9/64—Circuits for processing colour signals
    • H04N9/643—Hue control means, e.g. flesh tone control
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N9/00—Details of colour television systems
    • H04N9/64—Circuits for processing colour signals
    • H04N9/646—Circuits for processing colour signals for image enhancement, e.g. vertical detail restoration, cross-colour elimination, contour correction, chrominance trapping filters
    • 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
    • G06T2207/10—Image acquisition modality
    • G06T2207/10004—Still image; Photographic image
    • 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
    • G06T2207/10—Image acquisition modality
    • G06T2207/10024—Color image
    • 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]
    • 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
    • G06T2207/20172—Image enhancement details
    • G06T2207/20182—Noise reduction or smoothing in the temporal domain; Spatio-temporal filtering
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/80—Camera processing pipelines; Components thereof
    • H04N23/84—Camera processing pipelines; Components thereof for processing colour signals

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Image Processing (AREA)
  • Image Analysis (AREA)
BR112022022218A 2020-05-13 2021-05-13 Ajuste de imagem com base em aprendizado de máquina BR112022022218A2 (pt)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US202063024417P 2020-05-13 2020-05-13
US17/316,567 US11983846B2 (en) 2020-05-13 2021-05-10 Machine learning based image adjustment
PCT/US2021/032316 WO2021231776A1 (en) 2020-05-13 2021-05-13 Machine learning based image adjustment

Publications (1)

Publication Number Publication Date
BR112022022218A2 true BR112022022218A2 (pt) 2022-12-13

Family

ID=78512175

Family Applications (1)

Application Number Title Priority Date Filing Date
BR112022022218A BR112022022218A2 (pt) 2020-05-13 2021-05-13 Ajuste de imagem com base em aprendizado de máquina

Country Status (8)

Country Link
US (1) US11983846B2 (cg-RX-API-DMAC7.html)
EP (1) EP4150559A1 (cg-RX-API-DMAC7.html)
JP (1) JP7758685B2 (cg-RX-API-DMAC7.html)
KR (1) KR20230011288A (cg-RX-API-DMAC7.html)
CN (1) CN115461780B (cg-RX-API-DMAC7.html)
BR (1) BR112022022218A2 (cg-RX-API-DMAC7.html)
PH (1) PH12022552427A1 (cg-RX-API-DMAC7.html)
WO (1) WO2021231776A1 (cg-RX-API-DMAC7.html)

Families Citing this family (37)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP7521259B2 (ja) * 2020-05-27 2024-07-24 ブラザー工業株式会社 学習済みの機械学習モデル、画像処理装置、および、機械学習モデルのトレーニング方法
JP7512150B2 (ja) * 2020-09-24 2024-07-08 キヤノン株式会社 情報処理装置、情報処理方法およびプログラム
EP4264539A1 (en) * 2020-12-18 2023-10-25 Koninklijke Philips N.V. Methods and systems for flexible denoising of images using disentangled feature representation field
JP2022129737A (ja) * 2021-02-25 2022-09-06 ソニーセミコンダクタソリューションズ株式会社 距離画像センサデバイス及び距離画像処理システム並びに距離データの伝送方法
JP7269607B2 (ja) * 2021-03-31 2023-05-09 学校法人明治大学 情報処理装置、情報処理方法、及びプログラム
US12034967B2 (en) * 2021-04-05 2024-07-09 Nvidia Corporation Superpixel generation and use
US12530740B2 (en) * 2021-05-19 2026-01-20 Nvidia Corporation Real time enhancement for streaming content
US11606544B2 (en) * 2021-06-08 2023-03-14 Black Sesame Technologies Inc. Neural network based auto-white-balancing
US11778305B2 (en) * 2021-06-18 2023-10-03 Qualcomm Incorporated Composite image signal processor
US11303800B1 (en) * 2021-07-13 2022-04-12 Shenzhen GOODIX Technology Co., Ltd. Real-time disparity upsampling for phase detection autofocus in digital imaging systems
TWI789071B (zh) * 2021-10-25 2023-01-01 瑞昱半導體股份有限公司 基於區域控制以及紋理合成進行圖像增強的圖像處理系統與相關圖像處理方法
CN114169395B (zh) * 2021-11-05 2024-09-06 华中科技大学 一种电力系统主导失稳模式识别模型构建方法及应用
US12035054B1 (en) * 2021-12-09 2024-07-09 Amazon Technologies, Inc. Color filter array interpolation for RGB-IR image sensors
US12108168B1 (en) 2021-12-09 2024-10-01 Amazon Technologies, Inc. Color filter array interpolation for RGB-IR image sensors
US20230186446A1 (en) * 2021-12-15 2023-06-15 7 Sensing Software Image processing methods and systems for low-light image enhancement using machine learning models
KR20230099227A (ko) * 2021-12-27 2023-07-04 삼성전자주식회사 영상 처리 장치 및 방법
CN114359087B (zh) * 2021-12-29 2025-06-03 青岛海信移动通信技术有限公司 一种图像处理方法、装置、设备及介质
CN114331903B (zh) * 2021-12-31 2023-05-12 电子科技大学 一种图像修复方法及存储介质
CN114677291B (zh) * 2022-02-25 2023-05-12 荣耀终端有限公司 一种图像处理方法、装置及相关设备
US12020364B1 (en) * 2022-04-07 2024-06-25 Bentley Systems, Incorporated Systems, methods, and media for modifying the coloring of images utilizing machine learning
US20230351562A1 (en) * 2022-04-28 2023-11-02 Samsung Electronics Co., Ltd. Standard dynamic range (sdr) to high dynamic range (hdr)inverse tone mapping using machine learning
US12062144B2 (en) 2022-05-27 2024-08-13 Snap Inc. Automated augmented reality experience creation based on sample source and target images
CN115034981B (zh) * 2022-05-27 2024-08-06 大连海事大学 一种基于嵌入式多特征融合的深度学习水下图像增强方法
CN115314604B (zh) * 2022-10-12 2023-03-24 杭州魔点科技有限公司 色彩校正矩阵的生成方法、系统、电子装置和存储介质
WO2024129062A1 (en) * 2022-12-12 2024-06-20 Zeku, Inc. Method and apparatus for unified multi-stage artificial intelligence-based image signal processing pipeline
KR102664214B1 (ko) * 2022-12-14 2024-05-10 고려대학교 산학협력단 질감 보존을 위한 자가-잔차 학습 기반 자가 감독 노이즈 제거 장치 및 방법
JP7598173B2 (ja) 2022-12-14 2024-12-11 高麗大学校産学協力団 テクスチャーの保存のための自己残差学習に基づく自己監督型ブラインド雑音装置及び方法
WO2024132660A1 (en) * 2022-12-22 2024-06-27 Koninklijke Philips N.V. Apparatus for processing a medical image
CN116248895B (zh) * 2023-05-06 2023-07-21 上海扬谷网络科技有限公司 虚拟现实全景漫游的视频云转码方法及系统
WO2024249260A1 (en) * 2023-05-29 2024-12-05 Google Llc Systems and methods for direct convolutional training and inference for image processing of color mosaic camera sensors
CN116991298B (zh) * 2023-09-27 2023-11-28 子亥科技(成都)有限公司 一种基于对抗神经网络的虚拟镜头控制方法
WO2025101282A1 (en) * 2023-11-09 2025-05-15 Qualcomm Incorporated Closed-loop image enhancement
CN122556089A (zh) * 2024-01-19 2026-08-11 华为技术有限公司 用于对表示图像数据的数据进行编码或解码的方法和装置
CN118379664B (zh) * 2024-05-09 2025-03-11 广东迅科睿晟科技有限公司 一种基于人工智能的视频识别方法及系统
US20250378525A1 (en) * 2024-06-05 2025-12-11 Nvidia Corporation Updating visual characteristics of frames for content streaming systems and applications
KR20260073093A (ko) * 2024-11-14 2026-05-21 삼성전자주식회사 이미지의 히스토그램을 평활화하는 전자 장치, 이의 동작 방법, 및 기록 매체
CN121616511B (zh) * 2026-01-29 2026-07-17 西安科技大学 一种矿井图像增强方法及装置

Family Cites Families (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4659631B2 (ja) * 2005-04-26 2011-03-30 富士重工業株式会社 車線認識装置
US8649555B1 (en) * 2009-02-18 2014-02-11 Lucasfilm Entertainment Company Ltd. Visual tracking framework
US8638342B2 (en) * 2009-10-20 2014-01-28 Apple Inc. System and method for demosaicing image data using weighted gradients
US8786625B2 (en) * 2010-09-30 2014-07-22 Apple Inc. System and method for processing image data using an image signal processor having back-end processing logic
US20130208976A1 (en) * 2012-02-13 2013-08-15 Nvidia Corporation System, method, and computer program product for calculating adjustments for images
JP2015088096A (ja) * 2013-11-01 2015-05-07 株式会社ソニー・コンピュータエンタテインメント 情報処理装置および情報処理方法
KR20160105264A (ko) * 2015-02-27 2016-09-06 삼성전자주식회사 영상 보정 장치 및 방법
US10460231B2 (en) * 2015-12-29 2019-10-29 Samsung Electronics Co., Ltd. Method and apparatus of neural network based image signal processor
US10701366B2 (en) * 2017-02-21 2020-06-30 Qualcomm Incorporated Deriving motion vector information at a video decoder
CN108229279B (zh) * 2017-04-14 2020-06-02 深圳市商汤科技有限公司 人脸图像处理方法、装置和电子设备
KR20240095362A (ko) * 2017-06-26 2024-06-25 파나소닉 인텔렉츄얼 프로퍼티 코포레이션 오브 아메리카 부호화 장치, 복호 장치, 부호화 방법 및 복호 방법
US11263782B2 (en) * 2017-10-11 2022-03-01 Qualcomm Incorporated Image signal processor for processing images
US10643306B2 (en) 2017-10-11 2020-05-05 Qualcomm Incoporated Image signal processor for processing images
US10579908B2 (en) * 2017-12-15 2020-03-03 Google Llc Machine-learning based technique for fast image enhancement
CN109191558B (zh) 2018-07-27 2020-12-08 深圳市商汤科技有限公司 图像打光方法和装置
CN110062160B (zh) * 2019-04-09 2021-07-02 Oppo广东移动通信有限公司 图像处理方法和装置
CN110490914B (zh) * 2019-07-29 2022-11-15 广东工业大学 一种基于亮度自适应和显著性检测的图像融合方法
US11776129B2 (en) * 2020-12-16 2023-10-03 Qualcomm Incorporated Semantic refinement of image regions

Also Published As

Publication number Publication date
US20210360179A1 (en) 2021-11-18
EP4150559A1 (en) 2023-03-22
US11983846B2 (en) 2024-05-14
CN115461780B (zh) 2026-02-10
CN115461780A (zh) 2022-12-09
PH12022552427A1 (en) 2024-01-08
WO2021231776A1 (en) 2021-11-18
JP2023525702A (ja) 2023-06-19
JP7758685B2 (ja) 2025-10-22
KR20230011288A (ko) 2023-01-20

Similar Documents

Publication Publication Date Title
PH12022552427A1 (en) Machine learning based image adjustment
BR112021019867A2 (pt) Alinhamento de kernel de recursos quânticos
BR112023025951A2 (pt) Processador compósito de sinal de imagem
BR112021021511A2 (pt) Mitigação de ransomware em aplicativos isolados e integrados
BR112023002200A2 (pt) Processamento de imagem baseado em categorização de objeto
BR112018014982A8 (pt) Conduzir transações usando dispositivos eletrônicos com credenciais não nativas
Kantee et al. Rump kernels no os? no problem!
BR112023001159A2 (pt) Técnicas de identificação de superfície transitável
BR112019006442A8 (pt) Método, dispositivo de computação e sistema para proporcionar eventos de agenda baseados em modelo com aprimoramento gráfico
BR112021019977A2 (pt) Interface de usuário configurada para facilitar a anotação de usuário para segmentação de instância dentro de amostra biológica
WO2018208869A3 (en) LEARNING-BASED APPROACH TO ALIGN IMAGES ACQUIRED BY DIFFERENT TERMS
BR112014027343A2 (pt) processamento de entrada com rastreamento ocular de usuário
BR112015014920A2 (pt) método para fornecer uma imagem de participantes em um evento, sistema de serviço de imageamento e método para propiciar desenvolvimento colaborativo para a segurança em um evento
BR112018074368A2 (pt) método e aparelho para converter dados de cor em notas musicais
BR112013031869A2 (pt) sistema e método para a geração de um mapa de registro de imagem, sistema de planejamento de terapia, um ou mais processadores, e, meio legível por computador não transitório
BRPI0520043A2 (pt) sistema de navegação, método para receber dados gráficos vetoriais, produto de programa de computador e portador de dados
ATE418113T1 (de) System und verfahren zur bereitstellung von codesignierungs-diensten
EA202191443A1 (ru) Системы и способы дополненной реальности с применением веб-браузеров
Kar Dhat syndrome: Will it reach a height or die soon?
CN109269404B (zh) 图像处理方法、装置及指纹识别设备
Oorzhak The reality of the present and its reflection in the Tuvan language
SURAІ BUSINESS ENVIRONMENTAL RESEARCH IN CONDITIONS OF GENERAL KNOWLEDGE OF REGIONAL MANAGEMENT
TH2001001588A (th) ระบบและวิธีการสำหรับการอำนวยความสะดวกการสร้างข้อมูลทางภูมิศาสตร์
Carpenter Other matters always matter: a critical reading of humanitarian and socially engaged art education practices
Aladashvili et al. The problems of management in small and medium business in Georgia