Abstract
Deep learning-based methods have achieved excellent performance in image-deraining tasks. Unfortunately, most existing deraining methods incorrectly assume a uniform rain streak distribution and a fixed fine-grained level. And this uncertainty of rain streaks will result in the model not being competent at repairing all fine-grained rain streaks. In addition, some existing convolution-based methods extend the receptive field mainly by stacking convolution kernels, which frequently results in inaccurate feature extraction. In this work, we propose momentum-contrast and large-kernel for multi-fine-grained deraining network (MOONLIT). To address the problem that the model is not competent at all fine-grained levels, we use the unsupervised dictionary contrastive learning method to treat different fine-grained rainy images as different degradation tasks. Then, to address the problem of inaccurate feature extraction, we carefully constructed a restoration network based on large-kernel convolution with a larger and more accurate receptive field. In addition, we designed a data enhancement method to weaken features other than rain streaks in order to be better classified for different degradation tasks. Extensive experiments on synthetic and real-world deraining datasets show that the proposed method MOONLIT achieves the state-of-the-art performance on some datasets. Code is available at https://github.com/awhitewhale/moonlit.
Similar content being viewed by others
Availability of data and materials
The code generated during and analysed during the current study are available in the github repository, https://github.com/awhitewhale/moonlit.
References
Pal SK, Pramanik A, Maiti J, Mitra P (2021) Deep learning in multi-object detection and tracking: state of the art. App Intell 51(9):6400–6429
Lin G, Milan A, Shen C, Reid I (2017) Refinenet: Multi-path refinement networks for high-resolution semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 1925–1934
Chen X, Pan J, Jiang K, Li Y, Huang Y, Kong C, Dai L, Fan Z (2022) Unpaired deep image deraining using dual contrastive learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 2017–2026
Li M, Xie Q, Zhao Q, Wei W, Gu S, Tao J, Meng D (2018) Video rain streak removal by multiscale convolutional sparse coding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 6644–6653
Jiang K, Wang Z, Yi P, Chen C, Huang B, Luo Y, Ma J, Jiang J (2020) Multi-scale progressive fusion network for single image deraining. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 8346–8355
Du Y, Xu J, Zhen X, Cheng M-M, Shao L (2020) Conditional variational image deraining. IEEE Tran Image Process 29:6288–6301
Rai SN, Saluja R, Arora C, Balasubramanian VN, Subramanian A, Jawahar C (2022) Fluid: Few-shot self-supervised image deraining. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp 3077–3086
Deng S, Wei M, Wang J, Feng Y, Liang L, Xie H, Wang FL, Wang M (2020) Detail-recovery image deraining via context aggregation networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 14560–14569
Wang P, Zhu H (2021) Single-image de-raining using joint filter and multi-scale deep alternate-connection dense network. Neurocomputing 457:306–321
Yasarla R, Sindagi VA, Patel VM (2020) Syn2real transfer learning for image deraining using gaussian processes. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 2726–2736
Tan F, Qian Y, Kong Y, Zhang H, Zhou D, Fan Y, Chen L (2021) Dbswin: transformer based dual branch network for single image deraining. J Intell Fuzzy Syst (Preprint), 1–15
Wang S, Liu Y, Qing Y, Wang C, Lan T, Yao R (2020) Detection of insulator defects with improved resnest and region proposal network. IEEE Access 8:184841–184850. https://doi.org/10.1109/ACCESS.2020.3029857
Liang H, Ji W, Wang R, Ma Y, Chen J, Chen M (2022) A scene-dependent sound event detection approach using multi-task learning. IEEE Sens J 22(18):17483–17489. https://doi.org/10.1109/JSEN.2021.3098325
Devlin J, Chang M-W, Lee K, Toutanova K (2018) Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805
Yang W, Wang S, Xu D, Wang X, Liu J (2020) Towards scale-free rain streak removal via self-supervised fractal band learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol 34, pp 12629–12636
Wang C, Xing X, Wu Y, Su Z, Chen J (2020) Dcsfn: deep cross-scale fusion network for single image rain removal. In: Proceedings of the 28th ACM International Conference on Multimedia, pp 1643–1651
Chen C, Li H (2021) Robust representation learning with feedback for single image deraining. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 7742–7751
Lin X, Huang Q, Huang W, Tan X, Fang M, Ma L (2021) Single image deraining via detail-guided efficient channel attention network. Comput Graph 97:117–125
Zhang J, Pan J, Ren J, Song Y, Bao L, Lau RW, Yang M-H (2018) Dynamic scene deblurring using spatially variant recurrent neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 2521–2529
Zhang Y, Tian Y, Kong Y, Zhong B, Fu Y (2020) Residual dense network for image restoration. IEEE Trans Pattern Anal Machine Intell 43(7):2480–2495
Yuntong Y, Changfeng Y, Yi C, Lin Z, Xile Z, Luxin Y, Yonghong T (2022) Unsupervised deraining: where contrastive learning meets self-similarity. arXiv preprint arXiv:2203.11509
Liu Y, Yue Z, Pan J, Su Z (2021) Unpaired learning for deep image deraining with rain direction regularizer. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp 4753–4761
Zou W, Wang Y, Fu X, Cao Y (2022) Dreaming to prune image deraining networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 6023–6032
Yi Q, Li J, Dai Q, Fang F, Zhang G, Zeng T (2021) Structure-preserving deraining with residue channel prior guidance. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp 4238–4247
Xiao J, Zhou M, Fu X, Liu A, Zha Z-J (2021) Improving de-raining generalization via neural reorganization. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp 4987–4996
Zhang H, Sindagi V, Patel VM (2019) Image de-raining using a conditional generative adversarial network. IEEE Trans Circuits Syst Video Technol 30(11):3943–3956
Mishra S, Shah A, Bansal A, Choi J, Shrivastava A, Sharma A, Jacobs D (2020) Learning visual representations for transfer learning by suppressing texture. arXiv preprint arXiv:2011.01901
Ding X, Zhang X, Han J, Ding G (2022) Scaling up your kernels to 31x31: revisiting large kernel design in CNNS. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 11963–11975
Zhang H, Patel VM (2018) Density-aware single image de-raining using a multi-stream dense network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 695–704
Fu X, Huang J, Zeng D, Huang Y, Ding X, Paisley J (2017) Removing rain from single images via a deep detail network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 3855–3863
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: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 12270–12279
Yang H, Zhou D, Cao J, Zhao Q, Li M (2022) Rainformer: a pyramid transformer for single image deraining. J Supercomput. https://doi.org/10.1007/s11227-022-04895-5
Shen H, Zhao Z-Q, Liao W, Tian W, Huang D-S (2022) Joint operation and attention block search for lightweight image restoration. Pattern Recognit 132:108909
Gao F, Mu X, Ouyang C, Yang K, Ji S, Guo J, Wei H, Wang N, Ma L, Yang B (2022) Mltdnet: an efficient multi-level transformer network for single image deraining. Neural Comput Appl 34:14013–14027
Yasarla R, Patel VM (2020) Confidence measure guided single image de-raining. IEEE Trans Image Process 29:4544–4555
Chen T, Kornblith S, Norouzi M, Hinton G (2020) A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp 1597–1607. PMLR
He K, Fan H, Wu Y, Xie S, Girshick R (2020) Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 9729–9738
Wang C, Shen Q, Wang X, Jiang G (2022) Momentum feature comparison network based on generative adversarial network for single image super-resolution. Signal Proces Image Commun 106:116726
Li B, Liu X, Hu P, Wu Z, Lv J, Peng X (2022) All-in-one image restoration for unknown corruption. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 17452–17462
Peng C, Zhang X, Yu G, Luo G, Sun J (2017) Large kernel matters–improve semantic segmentation by global convolutional network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 4353–4361
Feng H, Wang L, Li Y, Du A (2022) Lkasr: large kernel attention for lightweight image super-resolution. Knowl Based Syst 252:109376
Liu X, Shen F, Zhao J, Nie C (2022) Randommix: a mixed sample data augmentation method with multiple mixed modes. arXiv preprint arXiv:2205.08728
He K, Zhang X, Ren S, Sun J (2016) Identity mappings in deep residual networks. In: European Conference on Computer Vision, pp 630–645. Springer
Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, Lin S, Guo B (2021) Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp 10012–10022
Agarap AF (2018) Deep learning using rectified linear units (relu). arXiv preprint arXiv:1803.08375
Hadsell R, Chopra S, LeCun Y (2006) Dimensionality reduction by learning an invariant mapping. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’06), vol 2, pp 1735–1742. IEEE
Dai J, Qi H, Xiong Y, Li Y, Zhang G, Hu H, Wei Y (2017) Deformable convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp 764–773
Wang X, Yu K, Dong C, Loy CC (2018) Recovering realistic texture in image super-resolution by deep spatial feature transform. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 606–615
Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980
Contributors M (2018) MMCV: openMMLab computer vision foundation. https://github.com/open-mmlab/mmcv
Wang Z, Cun X, Bao J, Zhou W, Liu J, Li H (2022) Uformer: a general u-shaped transformer for image restoration. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 17683–17693
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
Mittal A, Moorthy AK, Bovik AC (2012) No-reference image quality assessment in the spatial domain. IEEE Trans Image Process 21(12):4695–4708
OpenAI: GPT-4 technical report (2023)
Geiger A, Lenz P, Urtasun R (2012) Are we ready for autonomous driving? the kitti vision benchmark suite. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp 3354–3361. https://doi.org/10.1109/CVPR.2012.6248074
Menze M, Geiger A (2015) Object scene flow for autonomous vehicles. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 3061–3070
Zhang K, Li D, Luo W, Ren W (2021) Dual attention-in-attention model for joint rain streak and raindrop removal. IEEE Trans Image Process 30:7608–7619
Zhang K, Li D, Luo W, Ren W, Liu W (2022) Enhanced spatio-temporal interaction learning for video deraining: faster and better. IEEE Trans Pattern Anal Machine Intell 45(1):1287–1293
Funding
This work was supported in part by the project of National Natural Science Foundation of China under Grant No. 62272178.
Author information
Authors and Affiliations
Contributions
Yifan Liu, Chuanbo Zhu, and Yugen Jian wrote the main manuscript text. Yifan Liu, Chao Sun, and Han Liang designed the deraining method. Yifan Liu, Jincai Chen, and Ping Lu improved the performance of the model and designed the ablation experiments. Yifan Liu performed the experiments. All authors reviewed the manuscript.
Corresponding author
Ethics declarations
Ethical approval
Not applicable.
Conflict of interest
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
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Liu, Y., Chen, J., Lu, P. et al. MOONLIT: momentum-contrast and large-kernel for multi-fine-grained deraining. J Supercomput 79, 15729–15759 (2023). https://doi.org/10.1007/s11227-023-05286-0
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11227-023-05286-0