计算机科学

计算机科学 ›› 2025, Vol. 52 ›› Issue (11A): 250200079-5.doi: 10.11896/jsjkx.250200079

• 计算机图形学&多媒体 • 上一篇    下一篇

基于DIL的遥感影像修复方法

蒋雨佳1, 李杭琪1, 孙宝丹1,2, 张心一1, 江俊慧1,2, 巩建光1,2   

  1. 1 哈尔滨工程大学计算机科学与技术学院 哈尔滨 150001
    2 智慧农场技术与系统全国重点实验室 哈尔滨 150001
  • 出版日期:2025-11-15 发布日期:2025-11-10
  • 通讯作者: 孙宝丹(sunbaodan@hrbeu.edu.cn)
  • 作者简介:jiangyujia@hrbeu.edu.cn
  • 基金资助:
    :黑龙江省重点研发计划(2022ZX01A23)

Remote Sensing Image Restoration Based on DIL

JIANG Yujia1, LI Hangqi1, SUN Baodan1,2, ZHANG Xinyi1, JIANG Junhui1,2, GONG Jianguang1,2   

  1. 1 College of Computer Science and Technology,Harbin Engineering University,Harbin 150001,China
    2 National Key Laboratory of Smart Farm Technologies and Systems,Harbin 150001,China
  • Online:2025-11-15 Published:2025-11-10
  • Supported by:
    Key R&D Program of Heilongjiang Province(2022ZX01A23).

PDF (PC)

10

摘要： 目前,遥感影像已广泛应用于环境监测、灾害管理等领域。但在影像采集过程中,传感器故障或外部环境等因素会导致遥感影像质量下降,进而影响其应用效果。DIL(Distortion Invariant representation Learning)算法通过对不同的失真程度与失真类型进行建模并利用因果关系中的“后门”准则推导出因果网络进行图像修复,具有较强的泛化能力。因此,将DIL算法应用于遥感影像修复领域,旨在充分利用已采集到的遥感影像数据,提高遥感影像的修复质量,更好地在环境监测、灾害管理等领域应用。此外,还在DIL算法的基础上对训练数据进行了归一化处理操作,以保证训练数据的变量唯一,使其能更好地处理遥感影像的修复问题。在实验部分,使用DIL算法对遥感影像分别进行了去噪、去雨、去模糊,实验结果表明DIL算法在遥感影像修复方面的效果要优于Noise2Noise,FFDNet,DnCNN,Restormer算法,显著提升了图像修复质量。

关键词: DIL算法, 归一化处理, 因果关系, 遥感图像修复

Abstract: Currently,remote sensing images are widely used in environmental monitoring,disaster management and other fields.However,sensor failure or external environment results in the degradation of image quality in image acquisition influencing the application of remote sensing images.The DIL algorithm models different distortion degrees and distortion types,and uses the “backdoor” criterion in causal inference to derive the causal network for image restoration with fairly strong generalization ability.Therefore,this paper applies the DIL algorithm to remote sensing image restoration to use the collected remote sensing image data improving the restoration quality of remote sensing images.In this way,this paper uses DIL algorithm to improve the application of remote sensing images in environmental monitoring,disaster management and other fields.In this paper,the training data is normalized on the basis of the DIL algorithm to ensure that the variables of the training data are unique,so that they can better deal with the repair problems of remote sensing images.In the experiments,the DIL algorithm is used to denoise,rain and deblur the remote sensing images.The experimental results show that the DIL algorithm is better than the Noise2Noise,FFDNet,DnCNN and Restormer algorithms in remote sensing image restoration,and the image restoration quality is significantly improved.

Key words: Distortion invariant representation learning algorithm, Normalization, Causality, Remote sensing image restoration

中图分类号: 

  • TP181
[1]SONG T T,HANG Y,SHI M L.HybridNoise Removal Technology for Remote Sensing Images Based on Deep Learning[J].Computer Literacy and Technology,2024,20(13):37-38,48.
[2]WANG X Y,CEHN L,LI M.Interpolation-based image inpainting algorithms[J].Journal of Shantou University:Natural Science Edition,2015,30(2):9.
[3]LIU F F.Image Restoration Based on Partial Differential Equations and Its Fast Algorithm[D].Nanjing:Nanjing University of Posts and Telecommunications,2024.
[4]SHEN J.Research on image restoration method based on sparse representation[D].Beijing:North China Electric Power University,2016.
[5]MAO X J,SHEN C H,YANG Y B.Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connections[J].arXiv:1606.08921,2016.
[6]HU Y,WANG Y,ZHANG J.DEAR-GAN:Degradation-Aware Face Restoration With GAN Prior[J].IEEE Transactions on Circuits and Systems for Video Technology,2023,33:4603-4615.
[7]PAN J W,YIN Y,LI Y B,et al.Restoration of Material Pore Structure Image Using Transformer Architecture [C]//2024 IEEE Conference on Artificial Intelligence(CAI).Singapore,2024:1214-1219.
[8]LI X,LI B,JIN X,et al.Learning Distortion Invariant Representation for Image Restoration from a Causality Perspective[C]//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).IEEE,2023:1714-1724.
[9]FINN C,ABBEEL P,LEVINE S.Model-agnostic meta-learning for fast adaptation of deep networks[C]//International Confe-rence on Machine Learning.PMLR,2017:1126-1135.
[10]PEARL J.Causal inference in statistics:An overview[J]Statistics surveys,2009,3:96-146.
[11]WEI X,PHUNG S L,BOUZERDOUM A,et al.Invariant image recognition under projective deformations:An image normalization approach[C]//2015 Visual Communications and Image Processing(VCIP).IEEE,2015:1-4.
[12]ZHANG K,ZUO W,CHEN Y,D,et al.Beyond a Gaussian Denoiser:Residual Learning of Deep CNN for Image Denoising[J].IEEE Transactions on Image Processing,2017,26(7):3142-3155.
[13]HE K M,ZHANG X Y,REN S Q,et al.Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2016:770-778.
[14]DABOV K,FOI A,KATKOVNIK V,et al.Image denoisingby sparse 3-D transform-domain collaborative filtering[J].IEEE Trans.Image Process,2007,16(8):2080-2095.
[15]ZHANG K,ZUO W,ZHANG L.FFDNet:Toward a Fast andFlexible Solution for CNN-Based Image Denoising[J].IEEE Transactions on Image Processing,2018,27(9):4608-4622.
[16]JAAKKO L,MUNKBERG J,HASSELGREN J,et al.Noise2Noise:Learning Image Restoration without Clean Data[J].arXiv:1803.04189,2018.
[17]JIA X,PENG Y,LI J,et al.Dual-Complementary Convolution Network for Remote-Sensing Image Denoising[J].IEEE Geos-cience and Remote Sensing Letters,2022,19:1-5.
[18]HAN L,ZHAO Y,LV H,et al.Remote Sensing Image Denoising Based on Deep and Shallow Feature Fusion and Attention Mechanism[J].Remote Sens.,2022,14:1243.
[19]LIU M,JIANG W,LIU W,et al.Dynamic Adaptive Attention-Guided Self-Supervised Single Remote-Sensing Image Denoising[J].IEEE Transactions on Geoscience and Remote Sensing,2023,61:1-11.
[20]GLYMOUR M,PEARL J,JEWELL N P.Preliminaries:Statistics and Causal Models[M]//Causal inference in statistics:A primer[J].John Wiley & Sons,2016:2-4.
[21]FINN C,ABBEEL P,LEVINE S.Model-agnostic meta-learning for fast adaptation of deep networks[C]//International Confe-rence on Machine Learning.PMLR,2017:1126-1135.
[22]ZAMIR S W,ARORA A,KHAN S,et al.Restormer:Efficient transformer for high-resolution image restoration[C]//Procee-dings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2022:5728-5739.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发