基于轻量级密集连接和跨尺度特征融合的图像去雨研究
Research on Image De-Raining Based on Lightweight Dense Connectivity and Cross-Scale Feature Fusion
摘要: 单幅图像中雨迹的存在常常会遮挡图像中背景信息，导致图像细节的丢失。针对这一问题，本文提出了一种基于轻量级密集连接和跨尺度特征融合的去雨算法。该算法引入从频域角度补充特征提取信息的模块和通道注意力模块，并与轻量级密集连接模块以串联的方式连接，以此为核心构建一种多尺度去雨网络，实现图像中雨迹的去除与背景恢复。相邻尺度间的特征信息由跨尺度特征融合模块进行融合，实现信息利用最大化，有效提升了去雨图像的整体视觉质量。实验结果表明，本文在公开的Rain200H、Rain200L和RainDrop上均获得出色的去雨效果。以Rain200L为例，本文去雨算法的PSNR值和SSIM值达到41.61 dB/0.9900，分别比次优结果提高了0.38 dB/0.06%。
Abstract: The presence of rain trails in a single image often obscures the background information in the image, leading to the loss of image details. To address this problem, this paper proposes a rain removal algorithm based on lightweight dense connectivity and cross-scale feature fusion. The algorithm introduces a module that supplements the feature extraction information from the frequency domain perspective and a channel attention module, which are connected in series with the lightweight dense connection module to construct a multi-scale rain removal network as the core to achieve feature extraction and background recovery. The feature information between adjacent scales is fused by the cross-scale feature fusion module to maximise the information utilisation, which effectively improves the overall visual quality of the de-rain image. Experimental results show that this paper obtains excellent rain removal effects on the publicly available Rain200H, Rain200L and RainDrop. Taking Rain200L as an example, the PSNR and SSIM values of this paper’s rain removal algorithm reach 41.61 dB/0.9900, which are 0.38 dB/0.06% higher than the sub-optimal results, respectively.
文章引用：王飞, 王振军. 基于轻量级密集连接和跨尺度特征融合的图像去雨研究[J]. 建模与仿真, 2025, 14(1): 709-720. https://doi.org/10.12677/mos.2025.141067

参考文献

[1] Kang, L.W., Lin, C.W. and Fu, Y.H. (2012) Automatic Single-Image-Based Rain Streaks Removal via Image Decomposition. IEEE Transactions on Image Processing, 21, 1742-1755. [Google Scholar] [CrossRef] [PubMed]
[2] Kim, J., Lee, C., Sim, J. and Kim, C. (2013) Single-Image Deraining Using an Adaptive Nonlocal Means Filter. 2013 IEEE International Conference on Image Processing, Melbourne, 15-18 September 2013, 914-917. [Google Scholar] [CrossRef] 
[3] Zhang, H. and Patel, V.M. (2018) Density-Aware Single Image De-Raining Using a Multi-Stream Dense Network. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, 18-23 June 2018, 695-704. [Google Scholar] [CrossRef] 
[4] Yasarla, R. and Patel, V.M. (2019) Uncertainty Guided Multi-Scale Residual Learning-Using a Cycle Spinning CNN for Single Image De-Raining. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, 15-20 June 2019, 8397-8406. [Google Scholar] [CrossRef] 
[5] Zhang, H., Sindagi, V. and Patel, V.M. (2020) Image De-Raining Using a Conditional Generative Adversarial Network. IEEE Transactions on Circuits and Systems for Video Technology, 30, 3943-3956. [Google Scholar] [CrossRef] 
[6] Yang, W., Tan, R.T., Feng, J., Guo, Z., Yan, S. and Liu, J. (2020) Joint Rain Detection and Removal from a Single Image with Contextualized Deep Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 42, 1377-1393. [Google Scholar] [CrossRef] [PubMed]
[7] Jiang, K., Wang, Z., Yi, P., Chen, C., Huang, B., Luo, Y., et al. (2020) Multi-Scale Progressive Fusion Network for Single Image Deraining. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, 13-19 June 2020, 8343-8352. [Google Scholar] [CrossRef] 
[8] Zamir, S.W., Arora, A., Khan, S., Hayat, M., Khan, F.S., Yang, M., et al. (2021) Multi-Stage Progressive Image Restoration. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, 20-25 June 2021, 14816-14826. [Google Scholar] [CrossRef] 
[9] Qian, R., Tan, R.T., Yang, W., Su, J. and Liu, J. (2018) Attentive Generative Adversarial Network for Raindrop Removal from a Single Image. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, 18-23 June 2018, 2482-2491. [Google Scholar] [CrossRef] 
[10] Wang, Q., Jiang, K., Wang, Z., Ren, W., Zhang, J. and Lin, C. (2024) Multi-scale Fusion and Decomposition Network for Single Image Deraining. IEEE Transactions on Image Processing, 33, 191-204. [Google Scholar] [CrossRef] [PubMed]
[11] Huang, G., Liu, Z., Van Der Maaten, L. and Weinberger, K.Q. (2017) Densely Connected Convolutional Networks. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, 21-26 July 2017, 2261-2269. [Google Scholar] [CrossRef] 
[12] Wang, C., Mark Liao, H., Wu, Y., Chen, P., Hsieh, J. and Yeh, I. (2020) CSPNet: A New Backbone That Can Enhance Learning Capability of CNN. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Seattle, 14-19 June 2020, 1571-1580. [Google Scholar] [CrossRef] 
[13] Kim, D., Heo, B. and Han, D. (2024) DenseNets Reloaded: Paradigm Shift Beyond ResNets and Vits. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T. and Varol, G., Eds., Computer Vision—ECCV 2024, Springer, 395-415. [Google Scholar] [CrossRef] 
[14] Chen, H., Chen, X., Lu, J. and Li, Y. (2024) Rethinking Multi-Scale Representations in Deep Deraining Transformer. Proceedings of the AAAI Conference on Artificial Intelligence, 38, 1046-1053. [Google Scholar] [CrossRef] 
[15] Mao, X., Liu, Y., Liu, F., Li, Q., Shen, W. and Wang, Y. (2023) Intriguing Findings of Frequency Selection for Image Deblurring. Proceedings of the AAAI Conference on Artificial Intelligence, 37, 1905-1913. [Google Scholar] [CrossRef] 
[16] Zhang, Y., Li, K., Li, K., Wang, L., Zhong, B. and Fu, Y. (2018) Image Super-Resolution Using Very Deep Residual Channel Attention Networks. In: Ferrari, V., Hebert, M., Sminchisescu, C. and Weiss, Y., Eds., Computer Vision—ECCV 2018, Springer, 294-310. [Google Scholar] [CrossRef] 
[17] Cho, S., Ji, S., Hong, J., Jung, S. and Ko, S. (2021) Rethinking Coarse-To-Fine Approach in Single Image Deblurring. 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, 10-17 October 2021, 4621-4630. [Google Scholar] [CrossRef] 
[18] Chen, X., Pan, J. and Dong, J. (2024) Bidirectional Multi-Scale Implicit Neural Representations for Image Deraining. 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, 16-22 June 2024, 25627-25636. [Google Scholar] [CrossRef] 
[19] Yang, W., Tan, R.T., Feng, J., Liu, J., Guo, Z. and Yan, S. (2017) Deep Joint Rain Detection and Removal from a Single Image. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, 21-26 July 2017, 1685-1694. [Google Scholar] [CrossRef] 
[20] Ren, D., Zuo, W., Hu, Q., Zhu, P. and Meng, D. (2019) Progressive Image Deraining Networks: A Better and Simpler Baseline. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, 15-20 June 2019, 3932-3941. [Google Scholar] [CrossRef] 
[21] Fu, X., Qi, Q., Zha, Z., Zhu, Y. and Ding, X. (2021) Rain Streak Removal via Dual Graph Convolutional Network. Proceedings of the AAAI Conference on Artificial Intelligence, 35, 1352-1360. [Google Scholar] [CrossRef] 
[22] Yi, Q., Li, J., Dai, Q., Fang, F., Zhang, G. and Zeng, T. (2021) Structure-Preserving Deraining with Residue Channel Prior Guidance. 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, 10-17 October 2021, 4218-4227. [Google Scholar] [CrossRef] 
[23] Zamir, S.W., Arora, A., Khan, S., Hayat, M., Khan, F.S. and Yang, M. (2022) Restormer: Efficient Transformer for High-Resolution Image Restoration. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, 18-24 June 2022, 5718-5729. [Google Scholar] [CrossRef] 
[24] Xiao, J., Fu, X., Liu, A., Wu, F. and Zha, Z. (2023) Image De-Raining Transformer. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45, 12978-12995. [Google Scholar] [CrossRef] [PubMed]
[25] Chen, X., Li, H., Li, M. and Pan, J. (2023) Learning a Sparse Transformer Network for Effective Image Deraining. 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, 17-24 June 2023, 5896-5905. [Google Scholar] [CrossRef] 
[26] Huynh-Thu, Q. and Ghanbari, M. (2008) Scope of Validity of PSNR in Image/Video Quality Assessment. Electronics Letters, 44, 800-801. [Google Scholar] [CrossRef] 
[27] Wang, Z., Bovik, A.C., Sheikh, H.R. and Simoncelli, E.P. (2004) Image Quality Assessment: From Error Visibility to Structural Similarity. IEEE Transactions on Image Processing, 13, 600-612. [Google Scholar] [CrossRef] [PubMed]
[28] Chen, S., Ye, T., Bai, J., Chen, E., Shi, J. and Zhu, L. (2023) Sparse Sampling Transformer with Uncertainty-Driven Ranking for Unified Removal of Raindrops and Rain Streaks. 2023 IEEE/CVF International Conference on Computer Vision (ICCV), Paris, 1-6 October 2023, 13060-13071. [Google Scholar] [CrossRef] 
[29] Eigen, D., Krishnan, D. and Fergus, R. (2013) Restoring an Image Taken through a Window Covered with Dirt or Rain. 2013 IEEE International Conference on Computer Vision, Sydney, 1-8 December 2013, 633-640. [Google Scholar] [CrossRef] 
[30] Isola, P., Zhu, J., Zhou, T. and Efros, A.A. (2017) Image-to-Image Translation with Conditional Adversarial Networks. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, 21-26 July 2017, 5967-5976. [Google Scholar] [CrossRef] 
[31] Quan, Y., Deng, S., Chen, Y. and Ji, H. (2019) Deep Learning for Seeing through Window with Raindrops. 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, 27 October-2 November 2019, 2463-2471. [Google Scholar] [CrossRef] 
[32] Quan, R., Yu, X., Liang, Y. and Yang, Y. (2021) Removing Raindrops and Rain Streaks in One Go. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, 20-25 June 2021, 9143-9152. [Google Scholar] [CrossRef] 

为你推荐