CN114830168A - 图像重建方法、电子设备和计算机可读存储介质 - Google Patents

图像重建方法、电子设备和计算机可读存储介质 Download PDF

Info

Publication number
CN114830168A
CN114830168A CN202080002800.0A CN202080002800A CN114830168A CN 114830168 A CN114830168 A CN 114830168A CN 202080002800 A CN202080002800 A CN 202080002800A CN 114830168 A CN114830168 A CN 114830168A
Authority
CN
China
Prior art keywords
image
feature
input image
maps
generate
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
CN202080002800.0A
Other languages
English (en)
Inventor
那彦波
张文浩
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.)
BOE Technology Group Co Ltd
Original Assignee
BOE Technology Group Co Ltd
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 BOE Technology Group Co Ltd filed Critical BOE Technology Group Co Ltd
Publication of CN114830168A publication Critical patent/CN114830168A/zh
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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
    • G06T3/4053—Scaling of whole images or parts thereof, e.g. expanding or contracting based on super-resolution, i.e. the output image resolution being higher than the sensor resolution
    • G06T3/4076—Scaling of whole images or parts thereof, e.g. expanding or contracting based on super-resolution, i.e. the output image resolution being higher than the sensor resolution using the original low-resolution images to iteratively correct the high-resolution images
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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; CALCULATING OR 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
    • G06T3/4053—Scaling of whole images or parts thereof, e.g. expanding or contracting based on super-resolution, i.e. the output image resolution being higher than the sensor resolution
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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; CALCULATING OR 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; CALCULATING OR 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)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)

Abstract

本公开提供了一种用于边缘设备的图像重建方法、电子设备和存储介质。图像重建方法包括：从第一尺度的输入图像提取低级别特征以生成多个第一特征图，多个第一特征图相比于输入图像均具有大于第一尺度的第二尺度；从输入图像提取低级别特征以生成多个第二特征图，多个第二特征图均具有第二尺度；基于多个第二特征图生成多个掩模图；基于多个掩模图和多个第一特征图生成多个中间特征图，多个中间特征图均具有第二尺度，基于多个中间特征图合成具有第二尺度的重建图像。该方法有助于在较低的资源消耗下实现较好的图像超分辨率重建效果。

Description

PCT国内申请，说明书已公开。

Claims (17)

  1. PCT国内申请，权利要求书已公开。
CN202080002800.0A 2020-11-16 2020-11-16 图像重建方法、电子设备和计算机可读存储介质 Pending CN114830168A (zh)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/129145 WO2022099710A1 (zh) 2020-11-16 2020-11-16 图像重建方法、电子设备和计算机可读存储介质

Publications (1)

Publication Number Publication Date
CN114830168A true CN114830168A (zh) 2022-07-29

Family

ID=81602069

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202080002800.0A Pending CN114830168A (zh) 2020-11-16 2020-11-16 图像重建方法、电子设备和计算机可读存储介质

Country Status (3)

Country Link
US (1) US11893710B2 (zh)
CN (1) CN114830168A (zh)
WO (1) WO2022099710A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116702876B (zh) * 2023-04-27 2024-04-12 贵州大学 一种基于预处理的图像对抗防御方法

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108133456A (zh) * 2016-11-30 2018-06-08 京东方科技集团股份有限公司 人脸超分辨率重建方法、重建设备以及计算机系统
CN109035260A (zh) * 2018-07-27 2018-12-18 京东方科技集团股份有限公司 一种天空区域分割方法、装置和卷积神经网络
US10304193B1 (en) * 2018-08-17 2019-05-28 12 Sigma Technologies Image segmentation and object detection using fully convolutional neural network
CN110415170A (zh) * 2019-06-24 2019-11-05 武汉大学 一种基于多尺度注意力卷积神经网络的图像超分辨率方法
CN110458758A (zh) * 2019-07-29 2019-11-15 武汉工程大学 一种图像超分辨率重建方法、系统及计算机存储介质
CN110770784A (zh) * 2017-06-21 2020-02-07 佳能株式会社 图像处理装置、成像装置、图像处理方法、程序、以及存储介质
CN111091576A (zh) * 2020-03-19 2020-05-01 腾讯科技（深圳）有限公司 图像分割方法、装置、设备及存储介质
US20200167943A1 (en) * 2018-11-28 2020-05-28 Nvidia Corporation 3d plane detection and reconstruction using a monocular image
CN111931781A (zh) * 2020-08-10 2020-11-13 商汤集团有限公司 图像处理方法及装置、电子设备和存储介质

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9154698B2 (en) * 2013-06-19 2015-10-06 Qualcomm Technologies, Inc. System and method for single-frame based super resolution interpolation for digital cameras
US11361403B2 (en) * 2017-02-24 2022-06-14 Deepmind Technologies Limited Iterative multiscale image generation using neural networks
KR102017996B1 (ko) * 2018-01-16 2019-09-03 한국과학기술원 라인 입력 및 출력을 이용한 이미지 처리 방법 및 장치
US10885608B2 (en) 2018-06-06 2021-01-05 Adobe Inc. Super-resolution with reference images
MX2020013580A (es) * 2018-09-30 2021-02-26 Boe Technology Group Co Ltd Aparato y metodo para procesamiento de imagenes y sistema para entrenamiento de red neuronal.
KR20210051242A (ko) * 2019-10-30 2021-05-10 삼성전자주식회사 멀티 렌즈 영상 복원 장치 및 방법
CN110827200B (zh) * 2019-11-04 2023-04-07 Oppo广东移动通信有限公司 一种图像超分重建方法、图像超分重建装置及移动终端
US11501415B2 (en) * 2019-11-15 2022-11-15 Huawei Technologies Co. Ltd. Method and system for high-resolution image inpainting
US11544815B2 (en) * 2019-11-18 2023-01-03 Advanced Micro Devices, Inc. Gaming super resolution
JP2023528697A (ja) * 2020-04-01 2023-07-06 京東方科技集團股▲ふん▼有限公司 コンピュータ実現方法、装置及びコンピュータプログラム製品
CN113591872A (zh) * 2020-04-30 2021-11-02 华为技术有限公司 一种数据处理系统、物体检测方法及其装置

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108133456A (zh) * 2016-11-30 2018-06-08 京东方科技集团股份有限公司 人脸超分辨率重建方法、重建设备以及计算机系统
CN110770784A (zh) * 2017-06-21 2020-02-07 佳能株式会社 图像处理装置、成像装置、图像处理方法、程序、以及存储介质
CN109035260A (zh) * 2018-07-27 2018-12-18 京东方科技集团股份有限公司 一种天空区域分割方法、装置和卷积神经网络
US10304193B1 (en) * 2018-08-17 2019-05-28 12 Sigma Technologies Image segmentation and object detection using fully convolutional neural network
US20200167943A1 (en) * 2018-11-28 2020-05-28 Nvidia Corporation 3d plane detection and reconstruction using a monocular image
CN110415170A (zh) * 2019-06-24 2019-11-05 武汉大学 一种基于多尺度注意力卷积神经网络的图像超分辨率方法
CN110458758A (zh) * 2019-07-29 2019-11-15 武汉工程大学 一种图像超分辨率重建方法、系统及计算机存储介质
CN111091576A (zh) * 2020-03-19 2020-05-01 腾讯科技（深圳）有限公司 图像分割方法、装置、设备及存储介质
CN111931781A (zh) * 2020-08-10 2020-11-13 商汤集团有限公司 图像处理方法及装置、电子设备和存储介质

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
孙劲光 等: "基于残差式神经网络的局部风格迁移方法", 《激光与光电子学进展》, vol. 57, no. 8, 30 April 2020 (2020-04-30), pages 1 - 8 *

Also Published As

Publication number Publication date
US20220351333A1 (en) 2022-11-03
US11893710B2 (en) 2024-02-06
WO2022099710A1 (zh) 2022-05-19

Similar Documents

Publication Publication Date Title
CN109949255B (zh) 图像重建方法及设备
CN112233038B (zh) 基于多尺度融合及边缘增强的真实图像去噪方法
US11954822B2 (en) Image processing method and device, training method of neural network, image processing method based on combined neural network model, constructing method of combined neural network model, neural network processor, and storage medium
WO2018205676A1 (zh) 用于卷积神经网络的处理方法和系统、和存储介质
US10198801B2 (en) Image enhancement using self-examples and external examples
CN110738605A (zh) 基于迁移学习的图像去噪方法、系统、设备及介质
CA3144236A1 (en) Real-time video ultra resolution
WO2022134971A1 (zh) 一种降噪模型的训练方法及相关装置
Zuo et al. Convolutional neural networks for image denoising and restoration
CN112819910A (zh) 基于双鬼注意力机制网络的高光谱图像重建方法
CN111047543A (zh) 图像增强方法、装置和存储介质
Zhai et al. An effective deep network using target vector update modules for image restoration
CN116863194A (zh) 一种足溃疡图像分类方法、系统、设备及介质
CN115035011A (zh) 一种融合策略下自适应RetinexNet的低照度图像增强方法
CN112200719B (zh) 图像处理方法、电子设备及可读存储介质
Xie et al. MWA-MNN: Multi-patch Wavelet Attention Memristive Neural Network for image restoration
WO2022099710A1 (zh) 图像重建方法、电子设备和计算机可读存储介质
CN117593187A (zh) 基于元学习和Transformer的遥感图像任意尺度超分辨率重建方法
CN111724309B (zh) 图像处理方法及装置、神经网络的训练方法、存储介质
Liu et al. Arbitrary-scale super-resolution via deep learning: A comprehensive survey
Xu et al. Attention‐based multi‐channel feature fusion enhancement network to process low‐light images
CN114586056A (zh) 图像处理方法及装置、设备、视频处理方法及存储介质
CN113792862B (zh) 基于级联注意力机制的改正单图生成对抗网络的设计方法
CN108416756B (zh) 一种基于机器学习的区域感知图像去噪方法
Din et al. Smart embedded system based on demosaicking for enhancement of surveillance systems

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