Abstract
Vision based applications routinely involve restoration as a preprocessing step, making it impossible to have separate architectures for different types of weather restoration. But, most of the existing methods focus on weather specific application. Further, the methods for multi-weather image restoration have high computational constraints. To overcome these limitations, we propose a compact transformer based network, with 4.5M parameters (1/10\(^{th}\) of the existing method) for unified (simultaneous) removal of rain, snow and hazy effect with single set of trained parameters. We propose two parallel streams to handle the degradations: First, original resolution transformer stream (ORTS) focuses mainly on extracting fine level features through original scales of the inputs. Second, multi-level feature aggregation stream (MFAS) learns different sizes of the weather degradations. Further, it also uses coarse outputs from the first stream and utilizes edge boosting skip connections (EBSC) for propagating crucial edge details essential for image restoration. Finally, we present a memory replay training approach for generalization of the proposed network on multi-weather degraded scenarios. Substantial experiments on synthetic as well as real-world images, along with extensive ablation studies, demonstrate that the proposed method performs competitively with the existing methods for multi-weather image restoration. The code is provided at https://github.com/AshutoshKulkarni4998/UMWTransformer.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Chen, D., et al.: Gated context aggregation network for image dehazing and deraining. In: 2019 IEEE Winter Conference On Applications Of Computer Vision (WACV), pp. 1375–1383. IEEE (2019)
Chen, H., et al.: Pre-trained image processing transformer. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12299–12310 (2021)
Chen, W.-T., Fang, H.-Y., Ding, J.-J., Tsai, C.-C., Kuo, S.-Y.: JSTASR: joint size and transparency-aware snow removal algorithm based on modified partial convolution and veiling effect removal. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12366, pp. 754–770. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58589-1_45
Chen, W.T., et al.: All snow removed: Single image desnowing algorithm using hierarchical dual-tree complex wavelet representation and contradict channel loss. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 4196–4205 (2021)
Chen, W.T., Huang, Z.K., Tsai, C.C., Yang, H.H., Ding, J.J., Kuo, S.Y.: Learning multiple adverse weather removal via two-stage knowledge learning and multi-contrastive regularization: Toward a unified model. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 17653–17662 (2022)
Chen, Y., Bai, W., Huang, Q., Xiao, J.: Efficient motion symbol detection and multi-kernel learning for aer object recognition. IEEE Transactions on Cognitive and Developmental Systems (2021). https://doi.org/10.1109/TCDS.2021.3122131
Chen, Z., Wang, Y., Yang, Y., Liu, D.: Psd: Principled synthetic-to-real dehazing guided by physical priors. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7180–7189 (2021)
Deng, S., et al.: Detail-recovery image deraining via context aggregation networks. In: Proceedings of the IEEE/CVF Conference On Computer Vision And Pattern Recognition, pp. 14560–14569 (2020)
Dong, H., et al.: Multi-scale boosted dehazing network with dense feature fusion. In: Proceedings of the IEEE/CVF Conference On Computer Vision And Pattern Recognition, pp. 2157–2167 (2020)
Dosovitskiy, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)
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, pp. 633–640 (2013)
Godard, C., Mac Aodha, O., Firman, M., Brostow, G.J.: Digging into self-supervised monocular depth estimation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 3828–3838 (2019)
He, K., Sun, J., Tang, X.: Single image haze removal using dark channel prior. IEEE Trans. Pattern Anal. Mach. Intell. 33(12), 2341–2353 (2010)
Itti, L., Koch, C., Niebur, E.: A model of saliency-based visual attention for rapid scene analysis. IEEE Trans. Pattern Anal. Mach. Intell. 20(11), 1254–1259 (1998)
Jia, T., Li, J., Zhuo, L., Li, G.: Effective meta-attention dehazing networks for vision-based outdoor industrial systems. IEEE Trans. Industr. Inf. 18(3), 1511–1520 (2022). https://doi.org/10.1109/TII.2021.3059020
Jiang, K., et al.: 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 (2020)
Kang, L.W., Lin, C.W., Fu, Y.H.: Automatic single-image-based rain streaks removal via image decomposition. IEEE Trans. Image Process. 21(4), 1742–1755 (2011)
Li, B., et al.: Benchmarking single-image dehazing and beyond. IEEE Trans. Image Process. 28(1), 492–505 (2019). https://doi.org/10.1109/TIP.2018.2867951
Li, J., Li, Y., Zhuo, L., Kuang, L., Yu, T.: Usid-net: Unsupervised single image dehazing network via disentangled representations. IEEE Trans. Multimedia (2022). https://doi.org/10.1109/TMM.2022.3163554
Li, M., Cao, X., Zhao, Q., Zhang, L., Gao, C., Meng, D.: Video rain/snow removal by transformed online multiscale convolutional sparse coding. arXiv preprint arXiv:1909.06148 (2019)
Li, R., Cheong, L.F., Tan, R.T.: Heavy rain image restoration: Integrating physics model and conditional adversarial learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1633–1642 (2019)
Li, R., Tan, R.T., Cheong, L.F.: All in one bad weather removal using architectural search. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3175–3185 (2020)
Li, X., Wu, J., Lin, Z., Liu, H., Zha, H.: Recurrent squeeze-and-excitation context aggregation net for single image deraining. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 262–277. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01234-2_16
Li, Y., Tan, R.T., Guo, X., Lu, J., Brown, M.S.: Rain streak removal using layer priors. In: Proceedings of the IEEE Conference On Computer Vision And Pattern Recognition. pp. 2736–2744 (2016)
Liu, R.W., Guo, Y., Lu, Y., Chui, K.T., Gupta, B.B.: Deep network-enabled haze visibility enhancement for visual iot-driven intelligent transportation systems. IEEE Trans. Industrial Inform. (2022). https://doi.org/10.1109/TII.2022.3170594
Liu, Y.F., Jaw, D.W., Huang, S.C., Hwang, J.N.: Desnownet: Context-aware deep network for snow removal. IEEE Trans. Image Process. 27(6), 3064–3073 (2018). https://doi.org/10.1109/TIP.2018.2806202
Luo, Y., Xu, Y., Ji, H.: Removing rain from a single image via discriminative sparse coding. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3397–3405 (2015)
Ranftl, R., Bochkovskiy, A., Koltun, V.: Vision transformers for dense prediction. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 12179–12188 (2021)
Redmon, J., Farhadi, A.: Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767 (2018)
Ren, D., Zuo, W., Hu, Q., Zhu, P., Meng, D.: Progressive image deraining networks: A better and simpler baseline. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3937–3946 (2019)
Salazar-Colores, S., Cabal-Yepez, E., Ramos-Arreguin, J.M., Botella, G., Ledesma-Carrillo, L.M., Ledesma, S.: A fast image dehazing algorithm using morphological reconstruction. IEEE Trans. Image Process. 28(5), 2357–2366 (2018)
Shin, J., Park, H., Paik, J.: Region-based dehazing via dual-supervised triple-convolutional network. IEEE Trans. Multimedia 24, 245–260 (2022). https://doi.org/10.1109/TMM.2021.3050053
Su, Z., Zhang, Y., Shi, J., Zhang, X.P.: Recurrent network knowledge distillation for image rain removal. IEEE Transactions on Cognitive and Developmental Systems (2021). https://doi.org/10.1109/TCDS.2021.3131045
Valanarasu, J.M.J., Yasarla, R., Patel, V.M.: Transweather: Transformer-based restoration of images degraded by adverse weather conditions. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2353–2363 (2022)
Wang, Y., Liu, S., Chen, C., Zeng, B.: A hierarchical approach for rain or snow removing in a single color image. IEEE Trans. Image Process. 26(8), 3936–3950 (2017)
Wang, Z., Cun, X., Bao, J., Zhou, W., Liu, J., Li, H.: 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 (June 2022)
Xu, J., Zhao, W., Liu, P., Tang, X.: An improved guidance image based method to remove rain and snow in a single image. Comput. Inform. Sci. 5(3), 49 (2012)
Yi, D., Fang, H., Hua, Y., Su, J., Quddus, M., Han, J.: Improving synthetic to realistic semantic segmentation with parallel generative ensembles for autonomous urban driving. IEEE Trans. Cognitive Developm. Syst. (2021). https://doi.org/10.1109/TCDS.2021.3117925
Yu, S., et al.: Content-adaptive rain and snow removal algorithms for single image. In: International Symposium on Neural Networks. pp. 439–448. Springer (2014). https://doi.org/10.1007/978-3-319-12436-0_49
Zamir, S.W., Arora, A., Khan, S., Hayat, M., Khan, F.S., Yang, M.H.: Restormer: Efficient transformer for high-resolution image restoration. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5728–5739 (June 2022)
Zamir, S.W., et al.: Multi-stage progressive image restoration. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 14821–14831 (2021)
Zhai, M., Chen, L., Tung, F., He, J., Nawhal, M., Mori, G.: Lifelong gan: Continual learning for conditional image generation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 2759–2768 (2019)
Zhang, H., Patel, V.M.: 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 (2018)
Zhang, J., Tao, D.: Famed-net: A fast and accurate multi-scale end-to-end dehazing network. IEEE Trans. Image Process. 29, 72–84 (2019)
Zhao, S., Zhang, L., Shen, Y., Zhou, Y.: Refinednet: A weakly supervised refinement framework for single image dehazing. IEEE Trans. Image Process. 30, 3391–3404 (2021)
Zheng, X., Liao, Y., Guo, W., Fu, X., Ding, X.: Single-image-based rain and snow removal using multi-guided filter. In: Lee, M., Hirose, A., Hou, Z.-G., Kil, R.M. (eds.) ICONIP 2013. LNCS, vol. 8228, pp. 258–265. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-42051-1_33
Acknowledgement
This work was supported by the Science and Engineering Research Board (DST-SERB), India, under Grant ECR/2018/001538.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Kulkarni, A., Phutke, S.S., Murala, S. (2023). Unified Transformer Network for Multi-Weather Image Restoration. In: Karlinsky, L., Michaeli, T., Nishino, K. (eds) Computer Vision – ECCV 2022 Workshops. ECCV 2022. Lecture Notes in Computer Science, vol 13802. Springer, Cham. https://doi.org/10.1007/978-3-031-25063-7_21
Download citation
DOI: https://doi.org/10.1007/978-3-031-25063-7_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-25062-0
Online ISBN: 978-3-031-25063-7
eBook Packages: Computer ScienceComputer Science (R0)