Research on Image Denoising and Super-Resolution Reconstruction Technology of Multiscale-Fusion Images

Table 3

SSIM experimental results.

Dataset	Gaussian noise figure	Gaussian filter	SRCNN	SRGAN	DNCNN	ESPCN	ESRGAN	ADGAN	MFGAN (proposed)
CIFAR-10	0.2	0.58	0.60	0.62	0.64	0.63	0.64	0.60	0.63
	0.05	0.62	0.64	0.67	0.67	0.66	0.69	0.63	0.68
CIFAR-100	0.2	0.58	0.60	0.63	0.64	0.61	0.65	0.62	0.63
	0.05	0.61	0.63	0.67	0.66	0.63	0.66	0.64	0.67
VOC2012	0.2	0.60	0.61	0.65	0.62	0.62	0.66	0.61	0.67
	0.05	0.63	0.63	0.68	0.67	0.66	0.69	0.66	0.70
RENOIR	0.2	0.63	0.58	0.64	0.63	0.63	0.65	0.63	0.65
	0.05	0.64	0.61	0.65	0.66	0.64	0.68	0.65	0.68
ImageNet1	0.2	0.56	0.57	0.61	0.61	0.62	0.65	0.61	0.61
	0.05	0.61	0.62	0.66	0.64	0.63	0.67	0.62	0.66
ImageNet2	0.2	0.59	0.59	0.61	0.62	0.61	0.64	0.61	0.63
	0.05	0.62	0.62	0.63	0.64	0.63	0.68	0.62	0.68
BSD100	0.2	0.60	0.62	0.63	0.62	0.62	0.64	0.60	0.62
	0.05	0.62	0.63	0.67	0.67	0.63	0.67	0.63	0.66