计算机科学 ›› 2025, Vol. 52 ›› Issue (5): 171-178.doi: 10.11896/jsjkx.240200020
苗壮, 崔浩然, 张启阳, 王家宝, 李阳
MIAO Zhuang, CUI Haoran, ZHANG Qiyang, WANG Jiabao, LI Yang
摘要： 大气湍流引起的图像退化严重影响了目标检测和图像识别等计算机视觉下游任务的性能。现有基于深度学习的大气湍流退化图像复原模型虽然取得了较好的效果,但未充分利用湍流效应的特征信息。为了获得更好的复原效果,提出了一种基于对比度学习的大气湍流退化图像复原方法。针对大气湍流退化引起的模糊与扭曲,设计了湍流缓解块。该块融合了基于Transformer的通道信息交互模块与基于CNN的空间信息交互模块,在全局和局部层面上抑制湍流对图像的干扰。同时,引入对比学习,将清晰图像和大气湍流退化图像视为正样本和负样本,在特征空间中拉近大气湍流复原网络的输出与正样本的距离,推远与负样本的距离,更有效地进行特征提取和图像复原。在Helen合成测试集和Places合成测试集上,所提方法分别达到了26.78 dB,22.42 dB的PSNR和0.790 9,0.682 0的SSIM,与现有的5种方法相比达到了最佳效果,更适用于提升大气湍流退化图像的质量。
中图分类号:
| [1]ROGGEMANN M C,WELSH B M,HUNT B R.Imagingthrough turbulence[M].CRC press,1996. [2]ANANTRASIRICHAI N,ACHIM A,KINGSBURY N G,et al.Atmospheric turbulence mitigation using complex wavelet-based fusion[J].IEEE Transactions on Image Processing,2013,22(6):2398-2408. [3]MAO Z,CHIMITT N,CHAN S H.Image reconstruction ofstatic and dynamic scenes through anisoplanatic turbulence[J].IEEE Transactions on Computational Imaging,2020,6:1415-1428. [4]ZHU X,MILANFAR P.Removing atmospheric turbulence via space-invariant deconvolution[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,35(1):157-170. [5]HIRSCH M,SRA S,SCHÖLKOPF B,et al.Efficient filter flow for space-variant multiframe blind deconvolution[C]//2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.IEEE,2010:607-614. [6]FRIED D L.Probability of getting a lucky short-exposure image through turbulence[J].JOSA,1978,68(12):1651-1658. [7]YASARLA R,PATEL V M.Learning to restore a single face image degraded by atmospheric turbulence using cnns[J].ar-Xiv:2007.08404,2020. [8]MAO Z,JAISWAL A,WANG Z,et al.Single frame atmosphericturbulence mitigation:A benchmark study and a new physics-inspired transformer model[C]//Computer Vision-ECCV 2022:17th European Conference,Tel Aviv,Israel,October 23-27,2022,Proceedings,Part XIX.Cham:Springer Nature Switzerland,2022:430-446. [9]ZHANG X,MAO Z,CHIMITT N,et al.Imaging through the atmosphere using turbulence mitigation transformer[J].arXiv:2207.06465,2022. [10]JAISWAL A,ZHANG X,CHAN S H,et al.Physics-DrivenTurbulence Image Restoration with Stochastic Refinement[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.2023:12170-12181. [11]VASWANI A,SHAZEER N,PARMAR N,et al.Attention is all you need[C]//Proceedings of the 31st International Confe-rence on Neural Information Processing Systems.2017:6000-6010. [12]WU H,QU Y,LIN S,et al.Contrastive learning for compactsingle image dehazing[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2021:10551-10560. [13]ZHANG Y,LI K,LI K,et al.Image super-resolution using very deep residual channel attention networks[C]//Proceedings of the European Conference on Computer Vision(ECCV).2018:286-301. [14]YANG W,TAN R T,FENG J,et al.Deep joint rain detection and removal from a single image[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:1357-1366. [15]CAI B,XU X,JIA K,et al.Dehazenet:An end-to-end system for single image haze removal[J].IEEE transactions on image processing,2016,25(11):5187-5198. [16]YASARLA R,PATEL V M.Learning to restore images de-graded by atmospheric turbulence using uncertainty[C]//2021 IEEE International Conference on Image Processing(ICIP).IEEE,2021. [17]ZAMIR S W,ARORA A,KHAN S,et al.Multi-stage progressive image restoration[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2021:14821-14831. [18]WANG Z,CUN X,BAO J,et al.Uformer:A general u-shaped transformer for image restoration[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2022:17683-17693. [19]CHEN H,WANG Y,GUO T,et al.Pre-trained image proces-sing transformer[C]//Proceedings of the IEEE/CVF Confe-rence on Computer Vision and Pattern Recognition.2021:12299-12310. [20]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. [21]CHEN L,CHU X,ZHANG X,et al.Simple baselines for image restoration[C]//European Conference on Computer Vision.Cham:Springer Nature Switzerland,2022:17-33. [22]SERMANET P,LYNCH C,HSU J,et al.Time-contrastive networks:Self-supervised learning from multi-view observation[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops(CVPRW).IEEE,2017:486-487. [23]OORD A,LI Y,VINYALS O.Representation learning with contrastive predictive coding[J].arXiv:1807.03748,2018. [24]CHEN T,KORNBLITH S,NOROUZI M,et al.A simpleframework for contrastive learning of visual representations[C]//International Conference on Machine Learning.PMLR,2020:1597-1607. [25]LIANG D,LI L,WEI M,et al.Semantically contrastive learning for low-light image enhancement[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2022:1555-1563. [26]WANG Y,XIONG J,YAN X,et al.USCFormer:Unified Transformer With Semantically Contrastive Learning for Image Dehazing[J].IEEE Transactions on Intelligent Transportation Systems,2023,24(10):11321-11333. [27]WU G,JIANG J,LIU X.A practical contrastive learning framework for single-image super-resolution[J].arXiv:2111.13924,2023. [28]YE Y,YU C,CHANG Y,et al.Unsupervised deraining:Where contrastive learning meets self-similarity[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2022:5821-5830. [29]HIRSCH M,SRA S,SCHÖLKOPF B,et al.Efficient filter flow for space-variant multiframe blind deconvolution[C]//2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.IEEE,2010:607-614. [30]CHAN S H.Tilt-then-blur or blur-then-tilt? clarifying the at-mospheric turbulence model[J].IEEE Signal Processing Letters,2022,29:1833-1837. [31]SHI W,CABALLERO J,HUSZÁR F,et al.Real-time singleimage and video super-resolution using an efficient sub-pixel convolutional neural network[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016:1874-1883. [32]SIMONYAN K,ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[J].arXiv:1409.1556,2014. [33]WANG Z,SIMONCELLI E P,BOVIK A C.Multiscale structuralsimilarity for image quality assessment[C]//The Thrity-Se-venth Asilomar Conference on Signals,Systems & Computers.IEEE,2003:1398-1402. [34]ZHAO H,GALLO O,FROSIO I,et al.Loss functions for image restoration with neural networks[J].IEEE Transactions on Computational Imaging,2016,3(1):47-57. [35]LIU Z,LUO P,WANG X,et al.Deep learning face attributes in the wild[C]//Proceedings of the IEEE International Conference on Computer Vision.2015:3730-3738. [36]MAO Z,CHIMITT N,CHAN S H.Accelerating atmospheric turbulence simulation via learned phase-to-space transform[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.2021:14759-14768. [37]LE V,BRANDT J,LIN Z,et al.Interactive facial feature localization[C]//Computer Vision-ECCV 2012:12th European Conference on Computer Vision,Florence,Italy,Part III 12.SpringerBerlin Heidelberg,2012:679-692. [38]ZHOU B,LAPEDRIZA A,KHOSLA A,et al.Places:A 10 million image database for scene recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,40(6):1452-1464. [39]KINGMA D P,BA J.Adam:A method for stochastic optimization[J].arXiv:1412.6980,2014. [40]LIANG J,CAO J,SUN G,et al.Swinir:Image restoration using swin transformer[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.2021:1833-1844. [41]CHEN F,WANG H.Design of fuzzy image quality restoration algorithm based on multi-channel visual attention[J].Journal of Jilin University(Engineering and Technology Edition),2023,53(9):2626-2631. |
|
||
首页