CN115735225A - 图像处理方法和图像处理装置 - Google Patents

图像处理方法和图像处理装置 Download PDF

Info

Publication number
CN115735225A
CN115735225A CN202180041397.7A CN202180041397A CN115735225A CN 115735225 A CN115735225 A CN 115735225A CN 202180041397 A CN202180041397 A CN 202180041397A CN 115735225 A CN115735225 A CN 115735225A
Authority
CN
China
Prior art keywords
image
input image
hyper
processing
frequency band
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
CN202180041397.7A
Other languages
English (en)
Inventor
张晓雯
侯耀林
彭剑威
胡伟
周春华
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.)
Huawei Technologies Co Ltd
Original Assignee
Huawei Technologies 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 Huawei Technologies Co Ltd filed Critical Huawei Technologies Co Ltd
Publication of CN115735225A publication Critical patent/CN115735225A/zh
Pending legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00Geometric image transformations in the plane of the image
    • G06T3/40Scaling of whole images or parts thereof, e.g. expanding or contracting

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)

Abstract

本申请提供一种图像处理方法和图像处理装置,涉及人工智能领域。该方法包括:获取输入图像;对输入图像进行分频,得到输入图像的多个频段分量,上述多个频段分量与超分神经网络中多个子网络一一对应;确定与多个频段分量中每个频段分量对应的子网络运算层数;利用超分神经网络对输入图像进行超分处理,得到与多个频段分量对应的多个超分处理结果;将上述多个超分处理结果合成为输出图像。该方案主要根据输入图像的多个频段的分量确定超分神经网络的每个子网络的运算层数,之后再利用超分神经网络输入图像进行处理,从而在保证了图像超分辨率处理的结果精度的同时,还减少了占用的运算资源,提高了处理效率。

Description

PCT国内申请,说明书已公开。

Claims (14)

  1. PCT国内申请,权利要求书已公开。
CN202180041397.7A 2021-06-28 2021-06-28 图像处理方法和图像处理装置 Pending CN115735225A (zh)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2021/102613 WO2023272414A1 (zh) 2021-06-28 2021-06-28 图像处理方法和图像处理装置

Publications (1)

Publication Number Publication Date
CN115735225A true CN115735225A (zh) 2023-03-03

Family

ID=84690897

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202180041397.7A Pending CN115735225A (zh) 2021-06-28 2021-06-28 图像处理方法和图像处理装置

Country Status (2)

Country Link
CN (1) CN115735225A (zh)
WO (1) WO2023272414A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117726543A (zh) * 2023-07-14 2024-03-19 荣耀终端有限公司 图像处理方法和装置

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11704771B2 (en) * 2017-12-01 2023-07-18 Huawei Technologies Co., Ltd. Training super-resolution convolutional neural network model using a high-definition training image, a low-definition training image, and a mask image
CN108805814B (zh) * 2018-06-07 2020-05-19 西安电子科技大学 基于多频段深度卷积神经网络的图像超分辨重建方法
CN110599401A (zh) * 2019-08-19 2019-12-20 中国科学院电子学研究所 遥感图像超分辨率重建方法、处理装置及可读存储介质
CN112446436A (zh) * 2020-12-11 2021-03-05 浙江大学 基于生成对抗网络的抗模糊无人驾驶车辆多目标跟踪方法

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117726543A (zh) * 2023-07-14 2024-03-19 荣耀终端有限公司 图像处理方法和装置

Also Published As

Publication number Publication date
WO2023272414A1 (zh) 2023-01-05

Similar Documents

Publication Publication Date Title
CN110827200B (zh) 一种图像超分重建方法、图像超分重建装置及移动终端
US10410327B2 (en) Shallow depth of field rendering
CN109996023B (zh) 图像处理方法和装置
US9741096B2 (en) Guided image upsampling using bitmap tracing
CN107563974B (zh) 图像去噪方法、装置、电子设备及存储介质
Ramanarayanan et al. Feature-based textures
KR100860968B1 (ko) 해상도 향상 장치 및 방법
CN103440674A (zh) 一种数字图像蜡笔特效的快速生成方法
CN107920202A (zh) 基于增强现实的视频处理方法、装置及电子设备
CN114449181B (zh) 图像和视频处理方法及其系统、数据处理设备、介质
Hu et al. Hybrid shift map for video retargeting
CN110992246A (zh) 影像的金字塔分层切片方法
CN111353955A (zh) 一种图像处理方法、装置、设备和存储介质
CN102572219B (zh) 移动终端及其图像处理方法
CN115735225A (zh) 图像处理方法和图像处理装置
CN111951171A (zh) Hdr图像生成方法、装置、可读存储介质及终端设备
WO2014114529A1 (en) Method and apparatus for performing single-image super-resolution
CN116091322B (zh) 超分辨率图像重建方法和计算机设备
CN116489457A (zh) 视频的显示控制方法、装置、设备、系统和存储介质
CN110852974A (zh) 图像抗锯齿处理方法、图像生成器的训练方法及装置
US20220138906A1 (en) Image Processing Method, Apparatus, and Device
US20230098437A1 (en) Reference-Based Super-Resolution for Image and Video Enhancement
Bonneel et al. Proxy-guided texture synthesis for rendering natural scenes
CN114782460A (zh) 图像分割模型的生成方法及图像的分割方法、计算机设备
CN113689333A (zh) 一种图像增强的方法及装置

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