Abstract
Single image rain streaks removal is a great challenging task in computer vision due to the uncertainty of the shape and size of rain streaks. Current methods attempted to adopt complex optimization processes or progressive refinement schemes. But these methods cause a significant impact on the efficiency of many real-time demanding applications. To address this problem, we propose a multi-level transformer deraining network which is an efficient single image rain removal model. Specifically, an efficient deraining network is constructed to extract rain streaks. We then employ cascade networks to extract feature information from deep high-level to shallow low-level layers. In addition, the multi-head self-attention mechanism is applied to extracting global information in the feature map at each level, which can highly improve the representational ability for rain streaks. Experimental results on both synthetic and real-world datasets have demonstrated the efficacy of our method, which uses less time costs and obtains comparable results in comparison to the state-of-the-art methods.
Similar content being viewed by others
References
Kim J, Sim J, Kim C (2015) Video deraining and desnowing using temporal correlation and low-rank matrix completion. IEEE Trans Image Process 24(9):2658–2670. https://doi.org/10.1109/TIP.2015.2428933
Chen H, Wang Y, Guo T, Xu C, Deng Y, Liu Z, Ma S, Xu C, Xu C, Gao W (2021) Pre-trained image processing transformer. In: IEEE conference on computer vision and pattern recognition, pp. 12299–12310
Ma T, Huang T, Zhao X, Lou Y (2017) Image deblurring with an inaccurate blur kernel using a group-based low-rank image prior. Inf Sci 408:213–233. https://doi.org/10.1016/j.ins.2017.04.049
Alajarmeh A, Salam RA, Abdulrahim K, Marhusin MF, Zaidan AA, Zaidan BB (2018) Real-time framework for image dehazing based on linear transmission and constant-time airlight estimation. Inf Sci 436–437:108–130. https://doi.org/10.1016/j.ins.2018.01.009
Kang L, Lin C, Fu Y (2012) Automatic single-image-based rain streaks removal via image decomposition. IEEE Trans Image Process 21(4):1742–1755. https://doi.org/10.1109/TIP.2011.2179057
Li Y, Tan RT, Guo X, Lu J, Brown MS (2016) Rain streak removal using layer priors, pp. 2736–2744
Fu X, Huang J, Zeng D, Huang Y, Ding X, Paisley JW (2017) Removing rain from single images via a deep detail network. In: IEEE conference on computer vision and pattern recognition, pp. 1715–1723
Li X, Wu J, Lin Z, Liu H, Zha H (2018) Recurrent squeeze-and-excitation context aggregation net for single image deraining. In: Computer Vision - ECCV 2018 - 15th European Conference. Lecture Notes in Computer Science, vol. 11211, pp. 262–277
Yang W, Tan RT, Feng J, Liu J, Guo Z, Yan S (2017) Deep joint rain detection and removal from a single image. In: IEEE conference on computer vision and pattern recognition, pp. 1685–1694
Yang Y, Lu H (2019) Single image deraining via recurrent hierarchy enhancement network. In: Amsaleg, L., Huet, B., Larson, M.A., Gravier, G., Hung, H., Ngo, C., Ooi, W.T. (eds.) Proceedings of the 27th ACM international conference on multimedia, MM, pp. 1814–1822
Ding J, Guo H, Zhou H, Yu J, He X, Jiang B (2021) Distributed feedback network for single-image deraining. Inf Sci 572:611–626. https://doi.org/10.1016/j.ins.2021.02.080
Li S, Araujo IB, Ren W, Wang Z, Tokuda EK, Junior RH, Junior RMC, Zhang J, Guo X, Cao X (2019) Single image deraining: a comprehensive benchmark analysis. In: IEEE conference on computer vision and pattern recognition, pp. 3838–3847
Wang Y, Song Y, Ma C, Zeng B (2020) Rethinking image deraining via rain streaks and vapors. In: Computer vision—ECCV 2020—16th European conference. Lecture Notes in Computer Science, vol. 12362, pp. 367–382
Wei Y, Zhang Z, Wang Y, Xu M, Yang Y, Yan S, Wang M (2021) Deraincyclegan: Rain attentive cyclegan for single image deraining and rainmaking. IEEE Trans Image Process 30:4788–4801. https://doi.org/10.1109/TIP.2021.3074804
Zhu J, Park T, Isola P, Efros AA (2017) Unpaired image-to-image translation using cycle-consistent adversarial networks. In: IEEE international conference on computer vision, pp. 2242–2251
Wei Y, Zhang Z, Wang Y, Zhang H, Zhao M, Xu M, Wang M (2021) Semi-deraingan: A new semi-supervised single image deraining. In: 2021 IEEE international conference on multimedia and expo (ICME), pp. 1–6 . IEEE
Wei Y, Zhang Z, Zhang H, Hong R, Wang M (2019) A coarse-to-fine multi-stream hybrid deraining network for single image deraining. In: IEEE international conference on data mining, pp. 628–637
Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. In: Advances in neural information processing systems 30: Annual conference on neural information processing systems 2017, December 4-9, 2017, Long Beach, CA, USA, pp. 5998–6008
Wang H, Xie Q, Zhao Q, Liang Y, Meng D (2021) Rcdnet: An interpretable rain convolutional dictionary network for single image deraining. CoRR https://arxiv.org/abs/2107.06808
Guo Q, Sun J, Juefei-Xu F, Ma L, Xie X, Feng W, Liu Y, Zhao J (2021) Efficientderain: Learning pixel-wise dilation filtering for high-efficiency single-image deraining, pp. 1487–1495
Garg K, Nayar SK (2004) Detection and removal of rain from videos. In: IEEE computer society conference on computer vision and pattern recognition, pp. 528–535
Ren W, Tian J, Han Z, Chan AB, Tang Y (2017) Video desnowing and deraining based on matrix decomposition. In: IEEE conference on computer vision and pattern recognition, pp. 2838–2847
Liu J, Yang W, Yang S, Guo Z (2019) D3r-net: dynamic routing residue recurrent network for video rain removal. IEEE Trans Image Process 28(2):699–712. https://doi.org/10.1109/TIP.2018.2869722
Wang D, Cui C (2017) Stochastic configuration networks ensemble with heterogeneous features for large-scale data analytics. Inf Sci 417:55–71. https://doi.org/10.1016/j.ins.2017.07.003
Wang D, Li M (2017) Stochastic configuration networks: fundamentals and algorithms. IEEE Trans Cybern 47(10):3466–3479. https://doi.org/10.1109/TCYB.2017.2734043
Ji Y, Zhang H, Gao F, Sun H, Wei H, Wang N, Yang B (2022) LGCNET: A local-to-global context-aware feature augmentation network for salient object detection. Inf Sci 584:399–416. https://doi.org/10.1016/j.ins.2021.10.055
Yang W, Tan RT, Wang S, Fang Y, Liu J (2021) Single image deraining: From model-based to data-driven and beyond. IEEE Trans Pattern Anal Mach Intell 43(11):4059–4077. https://doi.org/10.1109/TPAMI.2020.2995190
Zhang H, Patel VM (2018) Density-aware single image de-raining using a multi-stream dense network. In: IEEE conference on computer vision and pattern recognition, pp. 695–704
Zhang H, Sindagi V, Patel VM (2020) Image de-raining using a conditional generative adversarial network. IEEE Trans Circuits Syst Video Technol 30(11):3943–3956. https://doi.org/10.1109/TCSVT.2019.2920407
Li R, Cheong L, Tan RT (2019) Heavy rain image restoration: Integrating physics model and conditional adversarial learning. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019, pp. 1633–1642. Computer Vision Foundation / IEEE, ??? . https://doi.org/10.1109/CVPR.2019.00173
Mirza M, Osindero S (2014) Conditional generative adversarial nets. CoRR https://arxiv.org/abs/1411.1784
Zhang X, Zhou X, Lin M, Sun J (2018) Shufflenet: An extremely efficient convolutional neural network for mobile devices. In: IEEE conference on computer vision and pattern recognition, pp. 6848–6856
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: IEEE conference on computer vision and pattern recognition, pp. 770–778
Fan Z, Wu H, Fu X, Huang Y, Ding X (2018) Residual-guide network for single image deraining. In: ACM multimedia conference on multimedia conference, pp. 1751–1759
Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S, Uszkoreit J, Houlsby N (2021) An image is worth 16x16 words: transformers for image recognition at scale
Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13(4):600–612. https://doi.org/10.1109/TIP.2003.819861
Ren D, Zuo W, Hu Q, Zhu P, Meng D (2019) Progressive image deraining networks: a better and simpler baseline. In: IEEE conference on computer vision and pattern recognition, pp. 3937–3946
Wang T, Yang X, Xu K, Chen S, Zhang Q, Lau RWH (2019) Spatial attentive single-image deraining with a high quality real rain dataset. In: IEEE conference on computer vision and pattern recognition, pp. 12270–12279
Qian R, Tan RT, Yang W, Su J, Liu J (2018) Attentive generative adversarial network for raindrop removal from a single image. In: IEEE conference on computer vision and pattern recognition, pp. 2482–2491
Huynh-Thu Q, Ghanbari M (2008) Scope of validity of PSNR in image/video quality assessment. Electron Lett 44(13):800–801
Yang W, Tan RT, Feng J, Guo Z, Yan S, Liu J (2020) Joint rain detection and removal from a single image with contextualized deep networks. IEEE Trans Pattern Anal Mach Intell 42(6):1377–1393. https://doi.org/10.1109/TPAMI.2019.2895793
Wei W, Meng D, Zhao Q, Xu Z, Wu Y (2019) Semi-supervised transfer learning for image rain removal. In: IEEE conference on computer vision and pattern recognition, pp. 3877–3886
Wang C, Xing X, Wu Y, Su Z, Chen J (2020) DCSFN: deep cross-scale fusion network for single image rain removal. In: MM ’20: The 28th ACM international conference on multimedia, pp. 1643–1651
Guo Z, Hou M, Sima M, Feng Z (2021) Derainattentiongan: unsupervised single-image deraining using attention-guided generative adversarial networks. Signal Image Video Process 16(1):185–192
Kingma DP, Ba J (2015) Adam: a method for stochastic optimization
Acknowledgements
This work was supported in part by the project of State Grid Shaanxi Electric Power Company Limited under Grant No. SGSNKYOOSPJS2100221, the Shenzhen Science and Technology Program under Grant no. JCYJ20210324131203009, and the HITSZ-J&A Joint Laboratory of Digital Design and Intelligent Fabrication under Grant no. HITSZ-J&A-2021A01.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Declarations
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Gao, F., Mu, X., Ouyang, C. et al. MLTDNet: an efficient multi-level transformer network for single image deraining. Neural Comput & Applic 34, 14013–14027 (2022). https://doi.org/10.1007/s00521-022-07226-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-022-07226-0