Landweber Iteration-Inspired Network for Image Super-Resolution

Table 4

Average PSNR/SSIM with degradation model BI , , and on five benchmarks. The best performances are shown in bold. The dash line means the paper does not report their performance.

Scale	Model	Set5 [50]	Set14 [51]	B100 [52]	Urban100 [53]	Manga109 [54]
		PSNR/SSIM	PSNR/SSIM	PSNR/SSIM	PSNR/SSIM	PSNR/SSIM
	SRCNN [13]	36.66/0.9542	32.42/0.9063	31.36/0.8879	29.50/0.8946	35.74/0.9661
	FSRCNN [29]	37.00/0.9558	32.63/0.9088	31.53/0.8920	29.88/0.9020	36.67/0.9694
	VDSR [14]	37.53/0.9587	33.03/0.9124	31.90/0.8960	30.76/0.9140	37.22/0.9729
	DRCN [58]	37.63/0.9588	33.04/0.9118	31.85/0.8942	30.75/0.9133	37.63/0.9723
	LapSRN [59]	37.52/0.9590	33.08/0.9130	31.80/0.8950	30.41/0.9100	37.27/0.9740
	SelNet [60]	37.89/0.9598	33.61/0.9160	32.08/0.8984	–	–
	RAN [61]	37.58/0.9592	33.10/0.9133	31.92/0.8963	–	–
	DNCL [62]	37.65/0.9599	33.18/0.9141	31.97/0.8971	30.89/0.9158	–
	FilterNet [63]	37.86/0.9610	33.34/0.9150	32.09/0.8990	31.24/0.9200	–
	MRFN [64]	37.98/0.9611	33.41/0.9159	32.14/0.8997	31.45/0.9221	38.29/0.9759
	SeaNet-baseline [65]	37.99/0.9607	33.60/0.9174	32.18/0.8995	32.08/0.9276	38.48/0.9768
	DEGREE [66]	37.58/0.9587	33.06/0.9123	31.80/0.8974	–	–
	FSN [67]	37.68/0.9065	33.51/0.9180	32.09/0.9015	31.68/0.9248	–
	MFSR [68]	38.07/0.9608	33.69/0.9191	32.22/0.9002	32.35/0.9307	38.75/0.9768
	LandNet (ours)	38.13/0.9609	33.89/0.9203	32.31/0.9013	32.74/0.9340	39.05/0.9778
	SRCNN [13]	32.75/0.9090	29.28/0.8209	28.41/0.7863	26.24/0.7989	30.59/0.9107
	FSRCNN [29]	33.16/0.9140	29.43/0.8242	28.53/0.7910	26.43/0.8080	30.98/0.9212
	VDSR [14]	33.66/0.9213	29.77/0.8314	28.82/0.7976	27.14/0.8279	32.01/0.9310
	DRCN [58]	33.82/0.9226	29.76/0.8311	28.80/0.7963	27.15/0.8276	32.31/0.9328
	DRRN [58]	34.03/0.9244	29.96/0.8349	28.95/0.8004	27.53/0.8378	32.74/0.9390
	SelNet [60]	34.27/0.9257	30.30/0.8399	28.97/0.8025	–	–
	RAN [61]	33.71/0.9223	29.84/0.8326	28.84/0.7981	–	–
	DNCL [62]	33.95/0.9232	29.93/0.8340	28.91/0.7995	27.27/0.8326	–
	FilterNet [63]	34.08/0.9250	30.03/0.8370	28.95/0.8030	27.55/0.8380	–
	MRFN [64]	34.21/0.9267	30.03/0.8363	28.99/0.8029	27.53/0.8389	32.82/0.9396
	SeaNet-baseline [65]	34.36/0.9280	30.34/0.8428	29.09/0.8053	28.17/0.8527	33.40/0.9444
	DEGREE [66]	33.76/0.9211	29.82/0.8326	28.74/0.7950	–	–
	DSRLN [69]	34.56/-	30.36/-	29.29/-	27.88/-	–
	MFSR [68]	34.49/0.9280	30.42/0.8442	29.16/0.8068	28.39/0.8577	33.72/0.9457
	LandNet (ours)	34.60/0.9288	30.47/0.8453	29.20/0.8081	28.63/0.8626	33.91/0.9471
	SRCNN [13]	30.48/0.8628	27.49/0.7503	26.90/0.7101	24.52/0.7221	27.66/0.8505
	FSRCNN [29]	30.71/0.8657	27.59/0.7535	26.98/0.7150	24.62/0.7280	27.90/0.8517
	VDSR [14]	31.35/0.8838	28.01/0.7674	27.29/0.7251	25.18/0.7524	28.83/0.8809
	DRCN [58]	31.53/0.8854	28.02/0.7670	27.23/0.7233	25.14/0.7510	28.98/0.8816
	LapSRN [59]	31.54/0.8850	28.19/0.7720	27.32/0.7280	25.21/0.7560	29.09/0.8845
	MemNet [56]	31.74/0.8893	28.26/0.7723	27.40/0.7281	25.50/0.7630	29.42/0.8942
	SelNet [60]	32.00/0.8931	28.49/0.7783	27.44/0.7325	–	–
	RAN [61]	31.43/0.8847	28.09/0.7691	27.31/0.7260	–	–
	DNCL [62]	31.66/0.8871	28.23/0.7717	27.39/0.7282	25.36/0.7606	–
	FilterNet [63]	31.74/0.8900	28.27/0.7730	27.39/0.7290	25.53/0.7680	–
	MRFN [64]	31.90/0.8916	28.31/0.7746	27.43/0.7309	25.46/0.7654	29.57/0.8962
	SeaNet-baseline [65]	32.18/0.8948	28.61/0.7822	27.57/0.7359	26.05/0.7896	30.44/0.9088
	DEGREE [66]	31.47/0.8837	28.10/0.7669	27.20/0.7216	–	–
	MFSR [68]	32.26/0.8961	28.65/0.7838	27.63/0.7381	26.25/0.7919	30.62/0.9103
	LandNet (ours)	32.39/0.8975	28.74/0.7857	27.66/0.7395	26.46/0.7983	30.88/0.9134

The values with bold type are the best ones within the experiments, which can show the advantages of our method in this paper.