Table 1 The quantitative results on benchmarks with Gaussian8 kernels.

From: A blind image super-resolution network guided by kernel estimation and structural prior knowledge

Method	Scale	Set5⁴³		Set14⁴⁴		BSD100⁴⁵		Urban100⁴⁶		Manga109⁴⁷
Method	Scale	PSNR	SSIM	PSNR	SSIM	PSNR	SSIM	PSNR	SSIM	PSNR	SSIM
Bicubic	x2	28.82	0.8577	26.02	0.7634	25.92	0.7310	23.14	0.7258	25.60	0.8498
CARN⁴⁸		30.99	0.8779	28.10	0.7879	26.78	0.7286	25.27	0.7630	26.86	0.8606
Bicubic+ZSSR¹³		31.08	0.8786	28.35	0.7933	27.92	0.7632	25.25	0.7618	28.05	0.8769
Deblurring⁴⁹+CARN⁴⁸		24.20	0.7496	21.12	0.6170	22.69	0.6471	18.89	0.5895	21.54	0.7946
CARN⁴⁸+Deblurring⁴⁹		31.27	0.8974	29.03	0.8267	28.72	0.8033	25.62	0.7981	29.58	0.9134
IKC¹		37.19	0.9526	32.94	0.9024	31.51	0.8790	29.85	0.8928	36.93	0.9667
DANv1⁵		37.34	0.9526	33.08	0.9041	31.76	0.8858	30.60	0.9060	37.23	0.9710
DANv2²		37.60	0.9544	33.44	0.9094	32.00	0.8904	31.43	0.9174	38.07	0.9734
DCLS³		37.63	0.9554	33.46	0.9103	32.04	0.8907	31.69	0.9202	38.31	0.9740
Ours		37.71	0.9548	33.56	0.9099	32.10	0.8912	31.80	0.9214	38.81	0.9745
Bicubic	x3	26.21	0.7766	24.01	0.6662	24.25	0.6356	21.39	0.6203	22.98	0.7576
CARN⁴⁸		27.26	0.7855	25.06	0.6676	25.85	0.6566	22.67	0.6323	23.85	0.7620
Bicubic+ZSSR¹³		28.25	0.7989	26.15	0.6942	26.06	0.6633	23.26	0.6534	25.19	0.7914
Deblurring⁴⁹+CARN⁴⁸		19.05	0.5226	17.61	0.4558	20.51	0.5331	16.72	0.5895	18.38	0.6118
CARN⁴⁸+Deblurring⁴⁹		30.31	0.8562	27.57	0.7531	27.14	0.7152	24.45	0.7241	27.67	0.8592
IKC¹		33.06	0.9146	29.38	0.8233	28.53	0.7899	24.43	0.8302	32.43	0.9316
DANv1⁵		34.04	0.9199	30.09	0.8287	28.94	0.7919	27.65	0.8352	33.16	0.9382
DANv2²		34.12	0.9209	30.20	0.8309	29.03	0.7948	27.83	0.8395	33.28	0.9400
DCLS³		34.21	0.9218	30.29	0.8329	29.07	0.7956	28.03	0.8444	33.54	0.9414
Ours		34.15	0.9213	30.40	0.8340	29.13	0.7978	28.30	0.8491	33.92	0.9436
Bicubic	x4	24.57	0.7108	22.79	0.6032	23.29	0.5786	20.35	0.5532	21.50	0.6933
CARN⁴⁸		26.57	0.7420	24.62	0.6226	24.79	0.5963	22.17	0.5865	21.85	0.6834
Bicubic+ZSSR¹³		26.45	0.7279	24.78	0.6268	24.97	0.5989	22.11	0.5805	23.53	0.7240
Deblurring⁴⁹+CARN⁴⁸		18.10	0.4843	16.59	0.3994	18.46	0.4481	15.47	0.3872	16.78	0.5371
CARN⁴⁸+Deblurring⁴⁹		28.69	0.8092	26.40	0.6926	26.10	0.6528	23.46	0.6597	25.84	0.8035
IKC¹		31.67	0.8829	28.31	0.7643	27.37	0.7192	25.33	0.7504	28.91	0.8782
DANv1⁵		31.89	0.8864	28.42	0.7687	27.51	0.7248	25.86	0.7721	30.50	0.9037
DANv2²		32.00	0.8885	28.50	0.7715	27.56	0.7277	25.94	0.7748	30.45	0.9037
AdaTarget¹⁴		31.58	0.8814	28.14	0.7626	27.43	0.7216	25.72	0.7683	29.97	0.8955
DCLS³		32.12	0.8890	28.54	0.7728	27.60	0.7285	26.15	0.7809	30.86	0.9086
Ours		32.07	0.8891	28.62	0.7747	27.63	0.7304	26.31	0.7860	30.98	0.9097

The best two results are marked in bold and italic, respectively.

Back to article page

Table 1 The quantitative results on benchmarks with Gaussian8 kernels.

Search

Quick links