Abstract
Rainy images severely degrade the visibility and make many computer vision algorithms invalid. Hence, it is necessary to remove rain streaks from single image. In this paper, we propose a novel network to handle with single image de-raining, which includes two modules: (a) multi-scale kernels de-raining layer and (b) multi-scale feature maps de-raining layer. Specifically, as spatial contextual information is important for single image de-raining, we develop a multi-scale kernels de-raining layer, which can utilize the multi-scale kernel that has receptive fields with different sizes to further capture the contextual information and these features are fused to learn the primary rain streaks structures. Moreover, we illustrate that convolution layers at different scales have similar structure of rain streaks by statistical pixel histogram and they can be processed in the same operation. So, we deal with the rain streaks information at different scales by using multi-scale kernels de-raining layers with shared parameters, where we call this operation as multi-scale feature maps de-raining layer. Finally, we employ dense connections to connect multi-scale feature maps de-raining layers to maximize the information flow along features from different levels. Quantitative and qualitative experimental results demonstrate the superiority of proposed method compared with several state-of-the-art de-raining methods, while the parameters of our proposed method are greatly reduced that benefits from the proposed shared parameters strategy at different scales
Similar content being viewed by others
References
Brewer N, Liu N (2008) Using the shape characteristics of rain to identify and remove rain from video. In: Structural, syntactic, and statistical pattern recognition, pp. 451–458. https://doi.org/10.1007/978-3-540-89689-0_49
Cai B, Xu X, Jia K, Qing C, Tao D (2016) Dehazenet: An end-to-end system for single image haze removal. In: IEEE Transactions on Image Processing. https://doi.org/10.1109/TIP.2016.2598681, vol 25, pp 5187–5198
Chen Y, Hsu C (2013) A generalized low-rank appearance model for spatio-temporally correlated rain streaks. In: ICCV, pp. 1968–1975. https://doi.org/10.1109/ICCV.2013.247
Cui Z, Chang H, Shan S, Zhong B, Chen X (2014) Deep network cascade for image super-resolution. In: ECCV, pp. 49–64. https://doi.org/10.1007/978-3-319-10602-1_4
Dong C, Loy CC, He K, Tang X (2016) Image super-resolution using deep convolutional networks. In: IEEE Trans Pattern Anal Mach Intell, vol 38, pp 295–307. https://doi.org/10.1109/TPAMI.2015.2439281
Fu X, Huang J, Ding X, Liao Y, Paisley J (2017) Clearing the skies: A deep network architecture for single-image rain removal. In: IEEE Transactions on Image Processing, vol 26, pp 2944–2956. https://doi.org/10.1109/TIP.2017.2691802
Fu X, Huang J, Zeng D, Huang Y, Ding X, Paisley J, Removing rain from single images via a deep detail network. In: CVPR pp. 1715–1723 (2017). https://doi.org/10.1109/CVPR.2017.186
Garg K, Nayar SK (2004) Detection and removal of rain from videos. In: CVPR, pp. 528–535. https://doi.org/10.1109/CVPR.2004.79
Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: CVPR, pp. 7132–7141. https://doi.org/10.1109/CVPR.2018.00745, http://openaccess.thecvf.com/content_cvpr_2018/html/H_Squeeze-and-Excitation_NetworksCVPR_2018_paper.html
Huang D, Kang L, Yang M, Lin C, Wang YF (2012) Context-aware single image rain removal. In: Proceedings of the 2012 IEEE International Conference on Multimedia and Expo, ICME 2012, Melbourne, Australia, July 9-13, 2012, pp. 164–169 . https://doi.org/10.1109/ICME.2012.92
Huang G, Liu Z, van der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: CVPR, pp. 2261–2269 . https://doi.org/10.1109/CVPR.2017.243
Huynh-Thu Q, Ghanbari M (2008) Scope of validity of psnr in image/video quality assessment. Electron Lett 44(13):800–801
Kang L, Lin C, Fu Y (2012) Automatic single-image-based rain streaks removal via image decomposition. In: IEEE Transactions on Image Processing, vol 21, pp 1742–1755. https://doi.org/10.1109/TIP.2011.2179057
Kim J, Lee C, Sim J, Kim C (2013) Single-image deraining using an adaptive nonlocal means filter. In: ICIP, pp. 914–917. https://doi.org/10.1109/ICIP.2013.6738189
Kingma DP, Ba J (2014) Adam: A method for stochastic optimization. In: CoRR, arXiv:1412.6980
Li Y, Tan RT, Guo X, Lu J, Brown MS (2016) Rain streak removal using layer priors. In: CVPR, pp. 2736–2744. https://doi.org/10.1109/CVPR.2016.299
Li B, Peng X, Wang Z, Xu J, Feng D (2017) Aod-net: All-in-one dehazing network. In: ICCV, pp. 4780–4788. https://doi.org/10.1109/ICCV.2017.511
Li G, He X, Zhang W, Chang H, Dong L, Lin L (2018) Non-locally enhanced encoder-decoder network for single image de-raining. In: ACM MM, pp. 1056–1064. https://doi.org/10.1145/3240508.3240636
Li X, Wu J, Lin Z, Liu H, Zha H (2018) Recurrent squeeze-and-excitation context aggregation net for single image deraining. In: ECCV, pp. 262–277. https://doi.org/10.1007/978-3-030-01234-2_16
Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, MA, USA, June 7-12, 2015, pp. 3431–3440. https://doi.org/10.1109/CVPR.2015.7298965
Luo Y, Xu Y, Ji H (2015) Removing rain from a single image via discriminative sparse coding. In: ICCV, pp. 3397–3405. https://doi.org/10.1109/ICCV.2015.388
Memos VA, Psannis KE, Ishibashi Y, Kim B, Gupta BB (2018) An efficient algorithm for media-based surveillance system (eamsus) in iot smart city framework. Future Generation Comp Syst 83:619–628. https://doi.org/10.1016/j.future.2017.04.039
Mustaniemi J, Kannala J, Särkkä S, Matas J, Heikkilä J (2018) Inertial-aided motion deblurring with deep networks. In: CoRR, arXiv:1810.00986
Plageras AP, Psannis KE, Stergiou C, Wang H, Gupta BB (2018) Efficient iot-based sensor BIG data collection-processing and analysis in smart buildings. Future Generation Comp Syst 82:349–357. https://doi.org/10.1016/j.future.2017.09.082
Psannis KE, Ishibashi Y (2006) Impact of video coding on delay and jitter in 3g wireless video multicast services. EURASIP J. Wireless Comm. and Networking 2006. https://doi.org/10.1155/WCN/2006/24616
Qian R, Tan RT, Yang W, Su J, Liu J (2018) Attentive generative adversarial network for raindrop removal from a single image. In: CVPR, pp. 2482–2491. https://doi.org/10.1109/CVPR.2018.00263, http://openaccess.thecvf.com/content_cvpr2018/html/Qian_Attentive_Generative_Adversarial_CVPR_2018_paper.html
Ren W, Liu S, Zhang H, Pan J, Cao X, Yang M (2016) Single image dehazing via multi-scale convolutional neural networks. In: ECCV, pp. 154–169. https://doi.org/10.1007/978-3-319-46475-6_10
Ren D, Zuo W, Hu Q, Zhu P, Meng D (2019) Progressive image deraining networks: a better and simpler baseline. IN: CVPR
Santhaseelan V, Asari VK (2015) Utilizing local phase information to remove rain from video. pp. 71–89 . https://doi.org/10.1007/s11263-014-0759-8
Stergiou C, Psannis K, Plageras A, Ishibashi Y, Kim BG (2018) Algorithms for efficient digital media transmission over iot and cloud networking. EURASIP J. Wireless Comm. and Networking 5(1):1–10. https://doi.org/10.1155/WCN/2006/24616
Stergiou C, Psannis KE, Kim B, Gupta BB (2018) Secure integration of iot and cloud computing. Future Generation Comp Syst 78:964–975. https://doi.org/10.1016/j.future.2016.11.031
Tripathi AK, Mukhopadhyay S (2014) Removal of rain from videos: a review. pp. 1421–1430. https://doi.org/10.1007/s11760-012-0373-6
Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Processing 13(4):600–612. https://doi.org/10.1109/TIP.2003.819861
Wang X, Shrivastava A, Gupta A (2017) A-fast-rcnn: Hard positive generation via adversary for object detection. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, July 21-26, 2017, pp. 3039–3048. https://doi.org/10.1109/CVPR.2017.324
Wang T, Yang X, Xu K, Chen S, Zhang Q, Lau RW (2019) Spatial attentive single-image deraining with a high quality real rain dataset. In: CVPR
Yang W, Tan RT, Feng J, Liu J, Guo Z, Yan S (2017) Deep joint rain detection and removal from a single image. In: CVPR, pp. 1685–1694. https://doi.org/10.1109/CVPR.2017.183
Yu J, Fan Y, Yang J, Xu N, Wang Z, Wang X, Huang T (2018) Wide activation for efficient and accurate image super-resolution. arXiv:1808.08718
Zhang H, Sindagi V, Patel VM (2017) Image de-raining using a conditional generative adversarial network. In: CoRR, arxiV:1701.05957
Zhang H, Patel VM (2018) Densely connected pyramid dehazing network. In: CVPR, pp. 3194–3203. https://doi.org/10.1109/CVPR.2018.00337, http://openaccess.thecvf.com/content_cvpr_2018/html/Zhang_Densely_Connected_Pyramid_CVPR_2018_paper.html
Zhang H, Patel VM (2018) Density-aware single image de-raining using a multi-stream dense network. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA, June 18-22, 2018, pp. 695–704. https://doi.org/10.1109/CVPR.2018.00079, http://openaccess.thecvf.com/content_cvpr_2018/html/Zhang_Density-Aware_Single_Image_CVPR_2018_paper.html
Zhang Y, Wang L, Qi J, Wang D, Feng M, Lu H (2018) Structured siamese network for real-time visual tracking. In: Computer Vision - ECCV 2018 - 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part IX, pp. 355–370. https://doi.org/10.1007/978-3-030-01240-3_22
Zhenghao Shi Yaning Feng MZLH (2019) A joint deep neural networks-based method for single nighttime rainy image enhancement Neural Computing and Applications
Acknowledgements
This work was supported by the Natural Science Foundation of China [grant numbers 61572099]; Major National Science and Technology Project of China [grant number 2018ZX04011001-007].
Author information
Authors and Affiliations
Corresponding author
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
Wang, C., Zhang, M., Su, Z. et al. Densely connected multi-scale de-raining net. Multimed Tools Appl 79, 19595–19614 (2020). https://doi.org/10.1007/s11042-020-08855-0
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-020-08855-0