Chinese Journal of Liquid Crystals and Displays, Volume. 38, Issue 10, 1409(2023)
Image rain removal algorithm based on multi-cascade progressive convolution structure
Fig. 2. Multi-cascade progressive convolution structure with lightweight parameters
Fig. 3. Schematic diagram of progressive cycle image deraining network structure
Fig. 4. Rain removal network based on multi-cascade progressive convolution structure
Fig. 5. Visualization results of artificially synthesized rainy day image dataset for rain removal experiment
Fig. 6. Visualization results of rain removal experiments on synthetic rainy image datasets in the field of autonomous driving
Fig. 8. Line chart of the experimental results（PSNR index）of different cycle times of the network
Fig. 9. Line chart of the experimental results（SSIM index）of different cycle times of the network
Table 1. Experimental hardware environment
View tableView in ArticleTable 1. Experimental hardware environment
实验硬件环境 环境配置 核心处理器 Intel Xeon Gold 5220@2.2 GHz 内存容量 256 GB 显卡型号 NVIDIA GeForce RTX 2080Ti
Table 2. Experimental software environment
View tableView in ArticleTable 2. Experimental software environment
实验软件环境 环境配置 服务器系统 Linux 7.6.1810 编程语言 Python 3.7.11 深度学习框架 Pytorch 1.7.1 开发工具 PyCharm 11.0.11；Matlab CUDA版本 10.1.243
Table 3. Experimental results of artificially synthesized rainy image dataset
View tableView in ArticleTable 3. Experimental results of artificially synthesized rainy image dataset
模型 评价指标 Rain100H Rain100L Rain800 GMM PSNR 14.26 29.11 21.27 SSIM 0.541 0.881 0.764 DDN PSNR 22.26 34.85 24.04 SSIM 0.690 0.950 0.867 RESCAN PSNR 26.60 37.07 24.09 SSIM 0.897 0.987 0.841 DCSFN PSNR 27.53 36.60 26.08 SSIM 0.890 0.979 0.864 PreNet PSNR 29.45 37.38 26.47 SSIM 0.899 0.978 0.889 AID-DWT PSNR 29.85 33.57 26.11 SSIM 0.902 0.958 0.876 本文方法 PSNR 30.70 37.91 27.63 SSIM 0.914 0.980 0.894
Table 4. Experimental results of synthetic rainy image datasets in the field of autonomous driving
View tableView in ArticleTable 4. Experimental results of synthetic rainy image datasets in the field of autonomous driving
模型 评价指标 BDD1000 GMM PSNR 24.33 SSIM 0.790 RESCAN PSNR 30.68 SSIM 0.924 DCSFN PSNR 31.44 SSIM 0.943 AID-DWT PSNR 33.08 SSIM 0.962 PreNet PSNR 35.07 SSIM 0.977 本文方法 PSNR 35.74 SSIM 0.977
Table 5. NIQE evaluation on real rainy images
View tableView in ArticleTable 5. NIQE evaluation on real rainy images
模型 真实雨图 NIQE评分 GMM Bike 14.984 Park 22.837 Road 19.235 DDN Bike 14.785 Park 23.811 Road 19.498 RESCAN Bike 12.473 Park 24.634 Road 19.507 DCSFN Bike 12.444 Park 21.356 Road 21.528 PreNet Bike 12.443 Park 22.908 Road 24.199 AID-DWT Bike 14.193 Park 22.513 Road 21.913 本文方法 Bike 12.408 Park 21.119 Road 18.336
Table 6. Ablation experiment results of different number of structural branches
View tableView in ArticleTable 6. Ablation experiment results of different number of structural branches
模型 评价指标 Rain100H Rain100L Rain800 结构A PSNR 30.70 37.91 27.63 SSIM 0.914 0.980 0.894 结构B PSNR 30.28 37.67 27.06 SSIM 0.910 0.980 0.891 结构C PSNR 30.62 37.81 27.15 SSIM 0.913 0.980 0.892 结构D PSNR 30.56 37.72 27.35 SSIM 0.912 0.980 0.892 基准方法 PSNR 29.45 37.38 26.47 SSIM 0.899 0.978 0.889
Table 7. Lightweight structure model experimental results
View tableView in ArticleTable 7. Lightweight structure model experimental results
模型 评价指标 Rain100H Rain100L Rain800 本文方法 PSNR 30.70 37.91 27.63 SSIM 0.914 0.980 0.894 轻量化改进的方法 PSNR 29.90 37.76 26.92 SSIM 0.905 0.980 0.890 基准方法 PSNR 29.45 37.38 26.47 SSIM 0.899 0.978 0.889
Table 8. Lightweight structure model parameter quantity and algorithm complexity
View tableView in ArticleTable 8. Lightweight structure model parameter quantity and algorithm complexity
模型 参数量 算法复杂度/GFLOPs 轻量化改进的方法 138 723 1.39 基准方法 168 963 1.69
Get Citation
Copy Citation Text
Yong ZHANG, Jie-long GUO, Fan WANG, Hai LAN, Hui YU, Xian WEI. Image rain removal algorithm based on multi-cascade progressive convolution structure[J]. Chinese Journal of Liquid Crystals and Displays, 2023, 38(10): 1409
Category: Research Articles
Received: Nov. 16, 2022
Accepted: --
Published Online: Oct. 25, 2023
The Author Email: Jie-long GUO (gjl@fjirsm.ac.cn)
