Abstract
Based on supervised learning, most of the existing single image deraining networks are trained on paired images including one clean image and one rain image. Since it is difficult to obtain a sufficient number of paired images, most of the rain images are manually synthesized from the clean ones. However, it costs huge time and effort, and requires professional experience to mimic the real rain images well. Moreover, the superior performance of these deraining networks trained on manually synthetic rain images is hard to be maintained when tested on real rain images. In this work, to obtain more realistic rain images for training supervised deraining networks, the depth-guided asymmetric CycleGAN (DA-CycleGAN) is proposed to translate clean images to their rainy counterparts automatically. Due to the cycle consistency strategy, DA-CycleGAN can also implement the single image deraining task unsupervised while synthesizing rain on clean images. Since rain streaks and rain mist vary with depth from the camera, DA-CycleGAN adopts depth information as an aid for rain synthesis and deraining. Furthermore, we design generators with different architectures for these two processes due to the information asymmetry in rain synthesis and deraining. Extensive experiments indicate that the DA-CycleGAN can synthesize more lifelike rain images and provide commensurate deraining performance compared with the state-of-the-art deraining methods.
Similar content being viewed by others
References
Arbeláez P, Maire M, Fowlkes C, Malik J (2011) Contour detection and hierarchical image segmentation. IEEE Trans Pattern Anal Mach Intell 33(5):898–916
Chen Y, Hsu C (2013) A generalized low-rank appearance model for spatio-temporally correlated rain streaks. In: 2013 IEEE international conference on computer vision (ICCV), pp 1968–1975
Choi Y, Choi M, Kim M, Ha J, Kim S, Choo J (2018) Stargan: unified generative adversarial networks for multi-domain image-to-image translation. In: 2018 IEEE/CVF conference on computer vision and pattern recognition (CVPR), pp 8789–8797
Deng J, Dong W, Socher R, Li L, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition (CVPR), pp 248–255
Eigen D, Puhrsch C, Fergus R (2014) Depth map prediction from a single image using a multi-scale deep network. In: Advances in neural information processing systems, pp 2366–2374
Fu X, Huang J, Ding X, Liao Y, Paisley J (2017) Clearing the skies: a deep network architecture for single-image rain removal. IEEE Trans Image Process 26(6):2944–2956
Fu X, Huang J, Zeng D, Huang Y, Ding X, Paisley J (2017) Removing rain from single images via a deep detail network. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR), pp 1715–1723
Garg K, Nayar SK (2006) Photorealistic rendering of rain streaks. In: ACM Trans Graphics, vol 25, pp 996–1002
Gerald S, Michal S (2004) UCID: an uncompressed color image database. In: Storage and retrieval methods and applications for multimedia 2004, vol 5307, pp 472–480
Godard C, Aodha OM, Brostow GJ (2017) Unsupervised monocular depth estimation with left-right consistency. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR), pp 6602–6611
Godard C, Aodha OM, Firman M, Brostow G (2019) Digging into self-supervised monocular depth estimation. In: 2019 IEEE/CVF international conference on computer vision (ICCV), pp 3827–3837
Goodfellow IJ, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y (2014) Generative adversarial nets. In: Proceedings of the 27th international conference on neural information processing systems (NIPS), pp 2672–2680
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), pp 770–778
Heusel M, Ramsauer H, Unterthiner T, Nessler B, Hochreiter S (2017) Gans trained by a two time-scale update rule converge to a local nash equilibrium. In: Neural information processing systems (NIPS)
Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(12):1735–80
Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M, Adam H (2017) Mobilenets: efficient convolutional neural networks for mobile vision applications
Hu X, Fu C, Zhu L, Heng P (2019) Depth-attentional features for single-image rain removal. In: 2019 IEEE/CVF conference on computer vision and pattern recognition (CVPR), pp 8014–8023
Huang X, Liu M, Belongie S, Kautz J (2018) Multimodal unsupervised image-to-image translation. In: European conference on computer vision (ECCV)
Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR), pp 2261–2269
Huynh-Thu Q, Ghanbari M (2008) Scope of validity of psnr in image/video quality assessment. Electron Lett 44(13):800–801
Iizuka S, Simo-Serra E, Ishikawa H (2017) Globally and locally consistent image completion. ACM Trans Graph 36(4):1–14
Isola P, Zhu J, Zhou T, Efros AA (2017) Image-to-image translation with conditional adversarial networks. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR), pp 1125–1134
Junbo JZ, Michaël M, Yann L (2016) Energy-based generative adversarial network. coRR
Kingma DP, Ba J (2015) Adam: a method for stochastic optimization. In: International conference on learning representations (ICLR)
Li R, Cheong L, Tan RT (2019) Heavy rain image restoration: integrating physics model and conditional adversarial learning. In: 2019 IEEE/CVF conference on computer vision and pattern recognition (CVPR), pp 1633–1642
Li Y, Tan RT, Guo X, Lu J, Brown MS (2016) Rain streak removal using layer priors. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), pp 2736–2744
Li X, Wu J, Lin Z, Liu H, Zha H (2018) Recurrent squeeze-and-excitation context aggregation net for single image deraining. In: European conference on computer vision (ECCV), pp 262–277
Liu M, Breuel T, Kautz J (2017) Unsupervised image-to-image translation networks. coRR
Liu F, Shen C, Lin G (2014) Deep convolutional neural fields for depth estimation from a single image. In: 2014 IEEE conference on computer vision and pattern recognition (CVPR), pp 5162–5170
Luo Y, Xu Y, Ji H (2015) Removing rain from a single image via discriminative sparse coding. In: 2015 IEEE international conference on computer vision (ICCV), pp 3397–3405
Mao X, Li Q, Xie H, Lau RY, Wang Z, Paul Smolley S (2017) Least squares generative adversarial networks. In: 2017 IEEE international conference on computer vision (ICCV), pp 2794–2802
Paszke A, Gross S, Massa F, Lerer A, Bradbury J, Chanan G, Killeen T, Lin Z, Gimelshein N, Antiga L et al (2019) Pytorch: an imperative style, high-performance deep learning library. In: Advances in neural information processing systems, pp 8026–8037
Ren D, Zuo W, Hu Q, Zhu P, Meng D (2019) Progressive image deraining networks: a better and simpler baseline. In: 2019 IEEE/CVF conference on computer vision and pattern recognition (CVPR), pp 3932–3941
Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. In: Medical image computing and computer-assisted intervention (MICCAI), pp 234–241
Saxena A, Chung SH, Ng AY (2006) Learning depth from single monocular images. In: Advances in neural information processing systems, pp 1161–1168
Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: International conference on learning representations (ICLR)
Tero K, Timo A, Samuli L, Jaakko L (2017) Progressive growing of gans for improved quality, stability, and variation. coRR
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
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: 2019 IEEE/CVF conference on computer vision and pattern recognition (CVPR), pp 12262–12271
Wei Y, Zhang Z, Wang Y, Fan J, Yan S, Wang M (2019) Deraincyclegan: a simple unsupervised network for single image deraining and rainmaking
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: 2019 IEEE international conference on data mining (ICDM), pp 628–637
Wofk D, Ma F, Yang T, Karaman S, Sze V (2019) Fastdepth: fast monocular depth estimation on embedded systems. In: ICRA, pp 6101–6108
Yang W, Tan RT, Feng J, Liu J, Guo Z, Yan S (2017) Deep joint rain detection and removal from a single image. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR), pp 1685–1694
Zhang H, Patel VM (2018) Density-aware single image de-raining using a multi-stream dense network. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR), 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
Zhu J, Park T, Isola P, Efros AA (2017) Unpaired image-to-image translation using cycle-consistent adversarial networks. In: 2017 IEEE international conference on computer vision (ICCV), pp 2242–2251
Acknowledgements
This work was supported by the National Natural Science Foundation of China (No. 62071500), Shenzhen Science and Technology Program (Grant No. GXWD20201231165807008, 2021A26).
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
Qi, Y., Zhang, H., Jin, Z. et al. Depth-guided asymmetric CycleGAN for rain synthesis and image deraining. Multimed Tools Appl 81, 35935–35952 (2022). https://doi.org/10.1007/s11042-022-13342-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-022-13342-9