Abstract
Despite the great success achieved by convolutional neural networks in addressing the raindrop removal problem, the still relatively blurry results call for better problem formulations and network architectures. In this paper, we revisited the rainy-to-clean translation networks and identified the issue of imbalanced distribution between raindrops and varied background scenes. None of the existing raindrop removal networks consider this underlying issue, thus resulting in the learned representation biased towards modeling raindrop regions while paying less attention to the important contextual regions. With the aim of learning a more powerful raindrop removal model, we propose learning a soft mask map explicitly for mitigating the imbalanced distribution problem. Specifically, a two stage network is designed with the first stage generating the soft masks, which helps learn a context-enhanced representation in the second stage. To better model the heterogeneously distributed raindrops, a multi-scale dense residual block is designed to construct the hierarchical rainy-to-clean image translation network. Comprehensive experimental results demonstrate the significant superiority of the proposed models over state-of-the-art methods.
Similar content being viewed by others
References
Qian R, Tan R T, Yang W, et al. Attentive generative adversarial network for raindrop removal from a single image. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, 2018. 2482–2491
Garg K, Nayar S K. Vision and rain. Int J Comput Vis, 2007, 75: 3–27
Xu X B, Wang Z, Deng Y M. A software platform for vision-based UAV autonomous landing guidance based on markers estimation. Sci China Tech Sci, 2019, 62: 1825–1836
Fu X, Huang J, Zeng D, et al. Removing rain from single images via a deep detail network. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Honolulu, 2017. 3855–3863
Yang W, Tan R T, Feng J, et al. Deep joint rain detection and removal from a single image. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Honolulu, 2017. 1357–1366
Zhang H, Patel V M. Density-aware single image de-raining using a multi-stream dense network. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, 2018. 695–704
Jiang K, Wang Z, Yi P, et al. Multi-scale progressive fusion network for single image deraining. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle, 2020. 8346–8355
Wang H, Xie Q, Zhao Q, et al. A model-driven deep neural network for single image rain removal. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle, 2020. 3103–3112
Wang C, Xing X, Wu Y, et al. DCSFN: Deep cross-scale fusion network for single image rain removal. In: Proceedings of the ACM International Conference on Multimedia. Seattle, 2020. 1643–1651
Wang T, Yang X, Xu K, et al. Spatial attentive single-image deraining with a high quality real rain dataset. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, 2019. 12270–12279
Wang G, Sun C, Sowmya A. ERL-Net: Entangled representation learning for single image de-raining. In: Proceedings of the IEEE International Conference on Computer Vision. Seoul, 2019. 5644–5652
Chang Y, Yan L, Zhong S. Transformed low-rank model for line pattern noise removal. In: Proceedings of the IEEE International Conference on Computer Vision. Venice, 2017. 1726–1734
Tanaka Y. Removal of adherent waterdrops from images acquired with a stereo camera system. IEICE Trans Inf Syst, 2006, 89: 2021–2027
Hara T, Saito H, Kanade T. Removal of glare caused by water droplets. In: Proceedings of the IEEE Conference for Visual Media Production. London, 2009. 144–151
You S, Tan R T, Kawakami R, et al. Adherent Raindrop Modeling, Detectionand Removal in Video. IEEE Trans Pattern Anal Mach Intell, 2016, 38: 1721–1733
Garg K, Nayar S K. Detection and removal of rain from videos. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, 2004. 325–332
Kurihata H, Takahashi T, Ide I, et al. Rainy weather recognition from in-vehicle camera images for driver assistance. In: Proceedings of the IEEE Intelligent Vehicles Symposium. Las Vegas, 2005. 205–210
Roser M, Kurz J, Geiger A. Realistic modeling of water droplets for monocular adherent raindrop recognition using Bézier curves. In: Proceedings of the Asian Conference on Computer Vision. Queenstown, 2011. 235–244
Simonyan K, Zisserman A. Very deep convolutional networks for largescale image recognition. In: Proceedings of the International Conference on Learning Representations. 2015. 325–332
Goodfellow I, Pouget-Abadie J, Mirza M, et al. Generative adversarial networks. Commun ACM, 2020, 63: 139–144
Badrinarayanan V, Kendall A, Cipolla R. SegNet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans Pattern Anal Mach Intell, 2017, 39: 2481–2495
Eigen D, Krishnan D, Fergus R. Restoring an image taken through a window covered with dirt or rain. In: Proceedings of the IEEE International Conference on Computer Vision. Sydney, 2013. 633–640
Isola P, Zhu J Y, Zhou T, et al. Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Honolulu, 2017. 1125–1134
Wang G, Sun C, Sowmya A. Attentive feature refinement network for single rainy image restoration. IEEE Trans Image Process, 2021, 30: 3734–3747
Wang G, Sun C, Sowmya A. Cascaded attention guidance network for single rainy image restoration. IEEE Trans Image Process, 2020, 29: 9190–9203
X Liu, Suganuma M, Sun Z, et al. Dual residual networks leveraging the potential of paired operations for image restoration. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, 2019. 7007–7016
Iizuka S, Simo-Serra E, Ishikawa H. Globally and locally consistent image completion. ACM Trans Graph, 2017, 36: 1–14
Kang L W, Lin C W, Fu Y H. Automatic single-image-based rain streaks removal via image decomposition. IEEE Trans Image Process, 2012, 21: 1742–1755
Chen Y, Hsu C T. Removing rain from a single image via discriminative sparse coding. In: Proceedings of the IEEE International Conference on Computer Vision. Santiago, 2015. 3397–3405
Roser M, Geiger A. Video-ased raindrop detection for improved image registration. In: Proceedings of the IEEE International Conference on Computer Vision Workshops. Kyoto, 2009. 570–577
Yu J, Lin Z, Yang J, et al. Generative image inpainting with contextual attention. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, 2018. 5505–5514
Pathak D, Krahenbuhl P, Donahue J, et al. Context encoders: Feature learning by inpainting. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Las Vegas, 2016. 2536–2544
Mao X, Li Q, Xie H, et al. Least squares generative adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision Workshops. Venice, 2017. 2794–2802
Xu D, Ouyang W, Wang X, et al. PAD-Net: Multi-tasks guided prediction-and-distillation network for simultaneous depth estimation and scene parsing. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, 2018. 675–684
Author information
Authors and Affiliations
Corresponding author
Additional information
This work was supported by the Joint Funds of the National Natural Science Foundation of China (Grant No. U20B2063), the Sichuan Science and Technology Program (Grant No. 2020YFS0057), and the Fundamental Research Funds for the Central Universities (Grant No. ZYGX2019Z015).
Rights and permissions
About this article
Cite this article
Wang, G., Yang, Y., Xu, X. et al. Enhanced context encoding for single image raindrop removal. Sci. China Technol. Sci. 64, 2640–2650 (2021). https://doi.org/10.1007/s11431-021-1914-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11431-021-1914-8