Image Deraining Algorithm via Multiflow Expansion Residual Dense Network

Weiwei Wang; Yayu Zhai; Ping Chen; Fengcai Cao

doi:10.3788/LOP202158.0410024

Journals >Laser & Optoelectronics Progress >Volume 58 >Issue 4 >Page 0410024 > Article

Laser & Optoelectronics Progress
Vol. 58, Issue 4, 0410024 (2021)

Image Deraining Algorithm via Multiflow Expansion Residual Dense Network

Weiwei Wang¹, Yayu Zhai², Ping Chen^1、*, and Fengcai Cao¹

Author Affiliations

¹School of Information and Communication Engineering, North University of China, Taiyuan, Shanxi 0 30051, China

²China Institute of Marine Technology&Economy, Beijing 100081, China;

show less

DOI: 10.3788/LOP202158.0410024 Cite this Article Set citation alerts

Weiwei Wang, Yayu Zhai, Ping Chen, Fengcai Cao. Image Deraining Algorithm via Multiflow Expansion Residual Dense Network[J]. Laser & Optoelectronics Progress, 2021, 58(4): 0410024 Copy Citation Text

show less

Fig. 1. Overall framework of image rain removal algorithm

Download full size

Fig. 2. Multiflow expansion residual dense network

Download full size

Fig. 3. Examples of image decomposition. (a) Rainy image; (b) base layer of rainy image; (c) base layer of rainless image; (d) detail layer of rainy image

Download full size

Fig. 4. Color curves of base layer. (a) Rainless image; (b) rainy image

Download full size

Fig. 5. Example of residual image. (a) Rainless image; (b) rainy image; (c) residual image

Download full size

Fig. 6. Visual comparison of different algorithms on composite rainy images. (a1)(a2) Rainy image; (b1)(b2) GMM algorithm; (c1)(c2) DSC algorithm; (d1)(d2) DCN algorithm; (e1)(e2) DID-MDN algorithm; (f1)(f2) MERDN algorithm

Download full size

Fig. 7. Visual comparison of different algorithms on real rainy images. (a1)(a2) Rainy image; (b1)(b2) GMM algorithm; (c1)(c2) DSC algorithm; (d1)(d2) DCN algorithm; (e1)(e2) DID-MDN algorithm; (f1)(f2) MERDN algorithm

Download full size

Layer	Filter size	Dilated factor	Number of filters
Convolution×1	3×3	1	32
Convolution×1	3×3	2	32
Convolution×1	3×3	3	32
Dense block×9	1×1	1	64
Dense block×9	3×3	2	32
Convolution×1	3×3	1	3

Table 1. Detailed setting of parameter layer

Algorithm	Dataset 1	Dataset 2	Dataset 3
GMM	23.75	28.36	30.70
DSC	22.03	24.16	30.02
DCN	21.97	28.17	29.42
ID-CGAN	23.81	23.39	20.78
DID-MDN	26.17	28.27	28.90
MERDN	26.46	28.81	31.90

Table 2. PSNR of different algorithms unit: dB

Algorithm	Dataset 1	Dataset 2	Dataset 3
GMM	0.7844	0.8712	0.8928
DSC	0.7985	0.8679	0.8679
DCN	0.8333	0.9134	0.9033
ID-CGAN	0.8072	0.8275	0.8519
DID-MDN	0.8409	0.8625	0.8762
MERDN	0.8841	0.9173	0.9381

Table 3. SSIM of different algorithms

Algorithm	GMM	DCN	DID-MDN	MERDN
Time /s	897	29	11	5

Table 4. Efficiency comparison of different algorithms

Weiwei Wang, Yayu Zhai, Ping Chen, Fengcai Cao. Image Deraining Algorithm via Multiflow Expansion Residual Dense Network[J]. Laser & Optoelectronics Progress, 2021, 58(4): 0410024

Download Citation

Set citation alerts for the article

Tools

Set citation alerts for the article

Save the article for my favorites

Paper Information