JP2023035928A - 一貫性損失に基づくニューラルネットワークのトレーニング - Google Patents

一貫性損失に基づくニューラルネットワークのトレーニング Download PDF

Info

Publication number
JP2023035928A
JP2023035928A JP2022132165A JP2022132165A JP2023035928A JP 2023035928 A JP2023035928 A JP 2023035928A JP 2022132165 A JP2022132165 A JP 2022132165A JP 2022132165 A JP2022132165 A JP 2022132165A JP 2023035928 A JP2023035928 A JP 2023035928A
Authority
JP
Japan
Prior art keywords
image
loss
output image
neural network
pixel values
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
JP2022132165A
Other languages
English (en)
Japanese (ja)
Other versions
JP2023035928A5 (enExample
Inventor
オレイフェジ、オマール
Oreifej Omar
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.)
Synaptics Inc
Original Assignee
Synaptics 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 Synaptics Inc filed Critical Synaptics Inc
Publication of JP2023035928A publication Critical patent/JP2023035928A/ja
Publication of JP2023035928A5 publication Critical patent/JP2023035928A5/ja
Pending legal-status Critical Current

Links

Images

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
    • 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
    • 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
    • G06N3/08—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
    • G06T5/00—Image enhancement or restoration
    • G06T5/70—Denoising; Smoothing
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
    • 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
    • G06T2207/20212—Image combination
    • G06T2207/20224—Image subtraction

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Software Systems (AREA)
  • Computing Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Linguistics (AREA)
  • Mathematical Physics (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Molecular Biology (AREA)
  • Multimedia (AREA)
  • Databases & Information Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Image Processing (AREA)
  • Image Analysis (AREA)
JP2022132165A 2021-09-01 2022-08-23 一貫性損失に基づくニューラルネットワークのトレーニング Pending JP2023035928A (ja)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US17/464,036 2021-09-01
US17/464,036 US12505344B2 (en) 2021-09-01 2021-09-01 Neural network training based on consistency loss

Publications (2)

Publication Number Publication Date
JP2023035928A true JP2023035928A (ja) 2023-03-13
JP2023035928A5 JP2023035928A5 (enExample) 2025-08-27

Family

ID=85286379

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2022132165A Pending JP2023035928A (ja) 2021-09-01 2022-08-23 一貫性損失に基づくニューラルネットワークのトレーニング

Country Status (4)

Country Link
US (1) US12505344B2 (enExample)
JP (1) JP2023035928A (enExample)
KR (1) KR20230033622A (enExample)
CN (1) CN115759195A (enExample)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP4517652A1 (en) 2023-08-29 2025-03-05 Canon Kabushiki Kaisha Information processing apparatus, training apparatus, and program

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US12327277B2 (en) 2021-04-12 2025-06-10 Snap Inc. Home based augmented reality shopping
US12412205B2 (en) 2021-12-30 2025-09-09 Snap Inc. Method, system, and medium for augmented reality product recommendations
US11928783B2 (en) * 2021-12-30 2024-03-12 Snap Inc. AR position and orientation along a plane
US12499626B2 (en) 2021-12-30 2025-12-16 Snap Inc. AR item placement in a video
WO2025230370A1 (ko) * 2024-04-29 2025-11-06 삼성전자 주식회사 신경망 모델을 사용하여 이미지를 처리하기 위한 방법 및 장치
CN119850751B (zh) * 2025-01-08 2025-08-12 北京中科思创云智能科技有限公司 基于海洋环境的几何一致性无监督双目标定方法

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10572979B2 (en) * 2017-04-06 2020-02-25 Pixar Denoising Monte Carlo renderings using machine learning with importance sampling
US10769761B2 (en) * 2017-06-30 2020-09-08 Kla-Tencor Corp. Generating high resolution images from low resolution images for semiconductor applications
WO2021230708A1 (en) * 2020-05-15 2021-11-18 Samsung Electronics Co., Ltd. Image processing method, electronic device and readable storage medium

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP4517652A1 (en) 2023-08-29 2025-03-05 Canon Kabushiki Kaisha Information processing apparatus, training apparatus, and program

Also Published As

Publication number Publication date
US12505344B2 (en) 2025-12-23
CN115759195A (zh) 2023-03-07
US20230063209A1 (en) 2023-03-02
KR20230033622A (ko) 2023-03-08

Similar Documents

Publication Publication Date Title
JP2023035928A (ja) 一貫性損失に基づくニューラルネットワークのトレーニング
CN111915526B (zh) 一种基于亮度注意力机制低照度图像增强算法的摄影方法
US11055828B2 (en) Video inpainting with deep internal learning
CN109255758B (zh) 基于全1*1卷积神经网络的图像增强方法
CN111681180B (zh) 先验驱动的深度学习图像去雾方法
CN111915525A (zh) 基于改进深度可分离生成对抗网络的低照度图像增强方法
CN112381897A (zh) 基于自编码网络结构的低照度图像增强方法
JP7512150B2 (ja) 情報処理装置、情報処理方法およびプログラム
US20220156891A1 (en) Methods and systems for deblurring blurry images
Li et al. Hdrnet: Single-image-based hdr reconstruction using channel attention cnn
Peng et al. Pdrf: progressively deblurring radiance field for fast scene reconstruction from blurry images
CN110580696A (zh) 一种细节保持的多曝光图像快速融合方法
CN114998141B (zh) 基于多分支网络的空间环境高动态范围成像方法
CN115049559B (zh) 模型训练、人脸图像处理、人脸模型处理方法及装置、电子设备及可读存储介质
CN117974459A (zh) 一种融合物理模型和先验的低照度图像增强方法
Prabhakar et al. Self-gated memory recurrent network for efficient scalable HDR deghosting
CN116894934A (zh) 基于场景自适应和自蒸馏的低光场景图像增强方法及系统
Shaw et al. HDR reconstruction from bracketed exposures and events
Singh et al. Weighted least squares based detail enhanced exposure fusion
CN116309077A (zh) 基于空域可变模糊核估计的图像盲超分辨率重建方法
Rana et al. Edge guided low-light image enhancement
Van Vo et al. High dynamic range video synthesis using superpixel-based illuminance-invariant motion estimation
CN114862709A (zh) 一种图像增强方法、装置及存储介质
Yang et al. Multi-scale extreme exposure images fusion based on deep learning
Cotogni et al. Select & Enhance: Masked-based image enhancement through tree-search theory and deep reinforcement learning

Legal Events

Date Code Title Description
A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20250819

A621 Written request for application examination

Free format text: JAPANESE INTERMEDIATE CODE: A621

Effective date: 20250819