Researching | Single image rain removal based on cross scale attention fusion

Opto-Electronic Engineering, Volume. 50, Issue 10, 230191-1(2023)

Single image rain removal based on cross scale attention fusion

Yuchao Ye and Ying Chen^*

Author Affiliations

Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education), Jiangnan University, Wuxi, Jiangsu 214122, China

show less

Abstract Get PDF(in Chinese)

Figures&Tables (15)

References (35)

Paper Information

Figures & Tables(15)

Fig. 1. Network structure

Download full size

View in Article

Fig. 2. Structure of MFA

Download full size

View in Article

Fig. 3. Visualization of features

Download full size

View in Article

Fig. 4. Feature extraction subnet network structure

Download full size

View in Article

Fig. 5. Multi-scale feature extraction block structure

Download full size

View in Article

Fig. 6. Rain200H typical picture examples

Download full size

View in Article

Fig. 7. Results of different algorithms on Rain200H dataset

Download full size

View in Article

Fig. 8. Different results of MSAFNet on DID-MDN dataset

Download full size

View in Article

Fig. 9. Comparison of PSNR/SSIM and time efficiency of each model in Rain200L and Rain200H datasets

Download full size

View in Article

Fig. 10. Experimental results of different algorithms on real-world dataset SPA-DATA

Download full size

View in Article

Fig. 11. Curve graph about the number of scales and subnets

Download full size

View in Article

Table 1. Comparison with other methods on synthetic datasets

View in Article

Table 1. Comparison with other methods on synthetic datasets

	Rain200H			Rain200L			Rain800		Params/M
	PSNR/dB	SSIM		PSNR/dB	SSIM		PSNR/dB	SSIM	Params/M
JORDER^[11]	23.54	0.805		36.11	0.974		23.47	0.869	3.89
LPNet^[12]	21.96	0.785		32.12	0.955		22.81	0.820	0.008
MSPFN^[13]	28.64	0.899		37.67	0.975		25.49	0.861	13.35
PReNet^[7]	27.81	0.891		36.47	0.982		25.18	0.853	0.16
RCDNet^[32]	29.27	0.899		38.52	0.985		26.38	0.872	2.99
MPRNe^[33]	29.32	0.915		37.35	0.980		26.10	0.895	20.6
BRN^[30]	28.96	0.908		37.71	0.983		25.88	0.857	0.39
RSGN^[31]	28.31	0.905		37.65	0.981		26.37	0.893	4.16
EfDeRain^[26]	25.54	0.884		31.51	0.957		24.16	0.839	27.61
MSAFNet	29.91	0.921		39.23	0.991		26.63	0.896	12.8

Table 2. Comparison with other methods on real dataset
View table
View in Article
Table 2. Comparison with other methods on real dataset
方法 MSPFN^[13] PReNet^[7] RCDNet^[32] MPRNet^[33] MSAFNet
NIQE↓ 4.921 5.013 4.881 4.903 4.816
SSEQ↓ 29.26 29.51 28.47 28.67 27.98

Table 3. Results of ablation experiments on the Rain200H dataset
View table
View in Article
Table 3. Results of ablation experiments on the Rain200H dataset
序号多尺度子网 MFA (Subnet) MFA (MFEB) PSNR/dB SSIM
1 × × × 26.76 0.871
2 √ × × 27.83 0.881
3 × × √ 27.92 0.884
4 √ √ × 28.51 0.898
5 √ × √ 29.47 0.916
6 √ √ √ 29.91 0.921

Table 4. The effect of subnet and MFEB scale number on PSNR
View table
View in Article
Table 4. The effect of subnet and MFEB scale number on PSNR
S=1 S=2 S=3 S=4
K=1 26.57 27.22 27.86 27.79
K=2 27.87 28.24 28.56 28.46
K=3 28.23 29.13 29.91 29.64
K=4 28.47 29.22 29.78 29.51

Tools

Get Citation

Copy Citation Text

Yuchao Ye, Ying Chen. Single image rain removal based on cross scale attention fusion[J]. Opto-Electronic Engineering, 2023, 50(10): 230191-1

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites

Paper Information

Category: Article

Received: Jul. 28, 2023

Accepted: Oct. 26, 2023

Published Online: Jan. 22, 2024

The Author Email: Ying Chen (陈莹)

DOI:10.12086/oee.2023.230191

Topics

laser devices and laser physics

Lasers and Laser Optics

laser manufacturing

Instrumentation, Measurement and Metrology