Abstract
Captured rainy images severely degrade outdoor vision systems performance, such as semi-autonomous or autonomous driving systems and video surveillance systems. Consequently, removing heavy and complex rain streaks, i.e. undesirable rainy artifacts from a rainy image, plays a crucial role for many high-level computer vision tasks and has drawn researchers’ attention over the past few years. The main drawbacks of convolutional neural networks are: have smaller receptive field, lack of model’s ability to capture long-range dependencies and complicated rainy artifacts, non-adaptive to input content and also increase in computational complexity quadratically with input image size. The aforementioned issues limit the performance of deraining model improvement further. Recently, transformer has achieved better performance in terms of both natural language processing (NLP) and high-level computer vision (CV). We cannot adopt transformer directly to image deraining as it has the following limitations: (a) although the transformer possesses powerful long-range computational capability, it lacks the ability to model local features, and (b) to process input image, transformer uses fixed patch size; therefore, pixels at the patch edges cannot use local features of surrounding pixels while removing heavy rain streaks. To address these issues, in single image deraining, we propose a novel and efficient deraining transformer (DeTformer). In DeTformer, we designed a “gated depth-wise convolution feed-forward network” (GDWCFN) to address the first issue and applied depth-wise convolution to improve the modelling capability of local features and suppress unnecessary features and allow only useful information to higher layers. Also, the second issue was addressed, by introducing multi-resolution features in our network, where we applied progressive learning in the transformer, and thus, it allows the edge pixels to utilize local features effectively. Furthermore, to integrate the extracted multi-scale features and provide feature interaction across channel dimensions, we introduced a “multi-head depth-wise convolution transposed attention” (MDWCTA) module. The proposed network was experimented with on various derained datasets and compared with state-of-the-art networks. The experimental results show that DeTformer network achieves superior performance compared to state-of-the-art networks on synthetic and real-world rain datasets.
Similar content being viewed by others
References
M.W. Ahmed, A.A. Abdulla, Quality improvement for exemplar-based image inpainting using a modified searching mechanism. UHD J Sci Technol 4(1), 1–8 (2020)
J.L. Ba, J.R. Kiros, G.E. Hinton, Layer normalization. arXiv preprint arXiv:1607.06450 (2016)
S. Cao, L. Liu, L. Zhao, Y. Xu, J. Xu, X. Zhang, Deep feature interactive aggregation network for single image deraining. IEEE Access 10, 103872–103879 (2022)
C. Chen, H. Li, 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 (2021)
H. Chen, Y. Wang, T. Guo, C. Xu, Y. Deng, Z. Liu, et al., Pre-trained image processing transformer, in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12299–12310 (2021)
L. Chen, X. Lu, J. Zhang, X. Chu, C. Chen, Hinet: half instance normalization network for image restoration, in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2021), pp. 182–192
Y.L. Chen, C.T. Hsu, A generalized low-rank appearance model for spatio-temporally correlated rain streaks, in Proceedings of the IEEE International Conference on Computer Vision (2013), pp. 1968–1975
S. Deng, M. Wei, J. Wang, Y. Feng, L. Liang, H. Xie, et al., Detail-recovery image deraining via context aggregation networks, in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2020), pp. 14560–14569
A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, et al., An image is worth 16 × 16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)
X. Fu, J. Huang, X. Ding, Y. Liao, J. Paisley, Clearing the skies: a deep network architecture for single-image rain removal. IEEE Trans. Image Process. 26(6), 2944–2956 (2017)
X. Fu, J. Huang, D. Zeng, Y. Huang, X. Ding, J. Paisley, Removing rain from single images via a deep detail network, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017), pp. 3855–3863
X. Fu, B. Liang, Y. Huang, X. Ding, J. Paisley, Lightweight pyramid networks for image deraining. IEEE Trans Neural Netw Learn Syst 31(6), 1794–1807 (2019)
X. Fu, Q. Qi, Z.J. Zha, Y. Zhu, X. Ding, Rain streak removal via dual graph convolutional network, in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 2 (2021), pp. 1352–1360
D. Hendrycks, K. Gimpel, Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415 (2016)
K. Jiang, Z. Wang, P. Yi, C. Chen, B. Huang, Y. Luo, et al., Multi-scale progressive fusion network for single image deraining, in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (2020), pp. 8346–8355
H. Ji, X. Feng, W. Pei, J. Li, G. Lu, U2-former: a nested u-shaped transformer for image restoration. arXiv preprint arXiv:2112.02279 (2021)
L.W. Kang, C.W. Lin, Y.H. Fu, Automatic single-image-based rain streaks removal via image decomposition. IEEE Trans. Image Process. 21(4), 1742–1755 (2011)
X. Li, J. Wu, Z. Lin, H. Liu, H. Zha, Recurrent squeeze-and-excitation context aggregation net for single image deraining, in Proceedings of the European Conference on Computer Vision (ECCV) (2018), pp. 254–269
Y. Li, Y. Monno, M. Okutomi, Single image deraining network with rain embedding consistency and layered LSTM, in Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (2022), pp. 4060–4069
Y. Li, R.T. Tan, X. Guo, J. Lu, M.S. Brown, Rain streak removal using layer priors, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016), pp. 2736–2744
Y. Li, K. Zhang, J. Cao, R. Timofte, L. Van Gool, Localvit: bringing locality to vision transformers. arXiv preprint arXiv:2104.05707 (2021)
X. Liu, M. Suganuma, Z. Sun, T. Okatani, 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 (2019), pp. 7007–7016
Z. Liu, Y. Lin, Y. Cao, H. Hu, Y. Wei, Z. Zhang, et al., Swin transformer: hierarchical vision transformer using shifted windows, in Proceedings of the IEEE/CVF International Conference on Computer Vision (2021), pp. 10012–10022
Y. Luo, Y. Xu, H. Ji, Removing rain from a single image via discriminative sparse coding, in Proceedings of the IEEE International Conference on Computer Vision (2015), pp. 3397–3405
C.B. Murthy, M.F. Hashmi, A.G. Keskar, EfficientLiteDet: a real-time pedestrian and vehicle detection algorithm. Mach. Vis. Appl. 33(3), 47 (2022)
T. Ragini, K. Prakash, Progressive multi-scale deraining network, in 2022 IEEE International Symposium on Smart Electronic Systems (iSES) (IEEE, 2022), pp. 231–235
D. Ren, W. Zuo, Q. Hu, P. Zhu, D. Meng, Progressive image deraining networks: a better and simpler baseline, in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2019), pp. 3937–3946
W. Shi, J. Caballero, F. Huszár, J. Totz, A.P. Aitken, R. Bishop, et al., Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016), pp. 1874–1883
F. Tan, Y. Kong, Y. Fan, F. Liu, D. Zhou, L. Chen, et al., SDNet: mutil-branch for single image deraining using swin. arXiv preprint arXiv:2105.15077 (2021)
J.M.J. Valanarasu, R. Yasarla, V.M. Patel, Transweather: transformer-based restoration of images degraded by adverse weather conditions, in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2022), pp. 2353–2363
A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A.N. Gomez, et al., Attention is all you need. in Advances in Neural Information Processing Systems (NIPS) (2017), pp. 5998–6008
H. Wang, Q. Xie, Q. Zhao, D. Meng, A model-driven deep neural network for single image rain removal, in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2020), pp. 3103–3112
T. Wang, L. Zhao, P. Huang, X. Zhang, J. Xu, Haze concentration adaptive network for image dehazing. Neurocomputing 439, 75–85 (2021)
Z. Wang, X. Cun, J. Bao, W. Zhou, J. Liu, H. Li, Uformer: a general u-shaped transformer for image restoration, in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2022), pp. 17683–17693
W. Wei, D. Meng, Q. Zhao, Z. Xu, Y. Wu, Semi-supervised transfer learning for image rain removal, in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2019), pp. 3877–3886
H. Wu, B. Xiao, N. Codella, M. Liu, X. Dai, L. Yuan, L. Zhang, Cvt: introducing convolutions to vision transformers, in Proceedings of the IEEE/CVF International Conference on Computer Vision (2021), pp. 22–31
H. Yang, D. Zhou, M. Li, Q. Zhao, A two-stage network with wavelet transformation for single-image deraining. Vis. Comput. 39, 3887–3903 (2023)
W. Yang, R.T. Tan, J. Feng, J. Liu, Z. Guo, S. Yan, Deep joint rain detection and removal from a single image, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017), pp. 1357–1366
W. Yang, R.T. Tan, S. Wang, Y. Fang, J. Liu, Single image deraining: From model-based to data-driven and beyond. IEEE Trans. Pattern Anal. Mach. Intell. 43(11), 4059–4077 (2020)
R. Yasarla, V.M. Patel, Uncertainty guided multi-scale residual learning-using a cycle spinning CNN for single image de-raining, in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2019), pp. 8405–8414
R. Yasarla, J.M.J. Valanarasu, V.M. Patel, Exploring overcomplete representations for single image deraining using cnns. IEEE J Sel Top Signal Process 15(2), 229–239 (2020)
H. Zhang, V.M. Patel, Density-aware single image de-raining using a multi-stream dense network, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018), pp. 695–704
H. Zhang, V.M. Patel, Convolutional sparse and low-rank coding-based rain streak removal, in 2017 IEEE Winter Conference on Applications of Computer Vision (WACV) (IEEE, 2017), pp. 1259–1267
H. Zhang, V. Sindagi, V.M. Patel, Image de-raining using a conditional generative adversarial network. IEEE Trans. Circuits Syst. Video Technol. 30(11), 3943–3956 (2019)
S. Zheng, C. Lu, Y. Wu, G. Gupta, SAPNet: segmentation-aware progressive network for perceptual contrastive deraining, in Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (2022), pp.52–62
X. Zhou, Q. Qiu, X. Huang, Deep joint rain detection and removal from a single image. IEEE Trans. Image Process. 28(2), 865–878 (2019)
Y. Zhu, Y. Su, P. Tan, A fast single image haze removal algorithm using color attenuation prior. IEEE Trans. Image Process. 24(11), 3522–3533 (2018)
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
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
Ragini, T., Prakash, K. & Cheruku, R. DeTformer: A Novel Efficient Transformer Framework for Image Deraining. Circuits Syst Signal Process 43, 1030–1052 (2024). https://doi.org/10.1007/s00034-023-02499-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00034-023-02499-9