Experimental results of the manuscript:

Weisheng Dong, Fazuo Fu, Guangming Shi, and Xun Cao, Jinjian Wu, Guangyu Li, and Xin Li, IEEE Trans. On Image Processing, vol. 25, no. 5, pp. 2337-2352, May 2016.

Matlab source code associated with this work can be downloaded from here. Code

Note:

(1) The hyperspectral image super-resolution method in [1] is labeled as “SNNMF”;

(2) The hyperspectral image super-resolution method in [2] is labeled as “CNMF”;

(3) The hyperspectral image super-resolution method in [3] is labeled as “MF”;

(4) The hyperspectral image super-resolution method in [4] is labeled as “GSOMP”;

(5) The hyperspectral image super-resolution method in [5] is labeled as “BSR”;

(6) The proposed hyperspectral image super-resolution method is labeled as “NSSR”.

Then, the reconstructed high-resolution hyperspectral image (HSI) by the method NSSR on the image cloth is labeled as “NSSR_cloth”. Other result images are labeled similarly.

Results on CAVE dataset (Uniform blur kernel)

Results on balloons_ms Download 8× Download 16× Download 32×

Results on cloth_ms Download 8× Download 16× Download 32×

Results on f_pepper_ms Download 8× Download 16× Download 32×

Note: f_pepper_ms denotes the fake_and_real_pepper_ms image in CAVE dataset.

Results on Harvard dataset (Uniform blur kernel)

Results on imga6 Download 8× Download 16× Download 32×

Results on imgb8 Download 8× Download 16× Download 32×

Results on imgd9 Download 8× Download 16× Download 32×

References:

[1] E. Wycoff, T. H. Chan, K. Jia, W. K. Ma, and Y. Ma, “A non-negative sparse promoting algorithm for high resolution hyperspectral imaging,” IEEE Int. Conf. Acoustics, Speech and Signal Processing (ICASSP), pp. 1409–1413, May 2013.

[2] N. Yokoya, T. Yairi, and A. Iwasaki, “Coupled nonnegative matrix factorization unmixing for hyperspectral and multispectral data fusion,” IEEE Trans. on Geosci. Remote Sens., vol. 50, no. 2, pp. 528–537, 2012.

[3] R. Kawakami, J. Wright, Y. W. Tai, Y. Matsushita, M. Ben-Ezra, and K. Ikeuchi, “High-resolution hyperspectral imaging via matrix factorization,” IEEE Conf. on Computer Vision and Pattern Recognition, pp. 2329–2336, 2011.

[4] N. Akhtar, F. Shafait and A. Mian, “Sparse spatio-spectral representation for hyperspectral image super-resolution,” European Conf. on Computer Vision (ECCV), pp. 63–78, 2014.

[5] Q. Wei, J. Bioucas-Dias, N. Dobigeon, and J. Tourneret, “Hyperspectral and multispectral image fusion based on a sparse representation,” IEEE Trans. on Geoscience and Remote Sensing, vol. 53, no. 7, pp. 3658-3668, July 2015.

Table 1 PSNR and RMSE results of the test methods on the CAVE dataset (Uniform blur kernel)

S=8
Methods	CNMF		MF		SNNMF		G-SOMP+		BSR		Proposed NSSR
	PSNR	RMSE	PSNR	RMSE	PSNR	RMSE	PSNR	RMSE	PSNR	RMSE	PSNR	RMSE
balloons	48.64	0.94	47.15	1.12	48.43	0.97	36.80	3.69	48.48	0.96	50.98	0.72
beads	35.42	4.32	34.56	4.77	35.41	4.33	28.47	9.61	35.15	4.46	37.48	3.41
cd	36.30	3.90	34.23	4.95	36.46	3.83	26.89	11.54	37.75	3.31	40.66	2.36
chart_toy	40.31	2.46	42.45	1.92	42.78	1.85	33.38	5.47	42.68	1.87	45.07	1.42
clay	47.76	1.04	45.65	1.33	47.15	1.12	40.34	2.45	47.55	1.07	49.12	0.89
cloth	36.27	3.92	36.72	3.72	37.10	3.56	32.44	6.09	36.72	3.72	39.07	2.84
eg_statue	47.69	1.05	46.61	1.19	48.14	1.00	38.33	3.09	49.22	0.88	49.14	0.89
face	46.18	1.25	44.14	1.58	44.97	1.44	38.13	3.16	45.58	1.34	46.98	1.14
f_beers	46.51	1.21	45.32	1.38	46.09	1.27	36.56	3.79	46.93	1.15	47.50	1.08
f_food	44.23	1.57	43.23	1.76	45.43	1.36	33.83	5.19	45.29	1.39	47.61	1.06
f_lemon_s	44.53	1.51	42.53	1.91	44.09	1.59	36.23	3.94	45.23	1.40	45.92	1.29
f_lemons	48.23	0.99	42.81	1.85	47.92	1.02	34.13	5.01	49.44	0.86	51.55	0.67
f_peppers	42.29	1.96	45.86	1.30	46.37	1.22	33.36	5.48	45.76	1.31	48.82	0.92
f_strawbe	46.89	1.15	44.20	1.57	47.06	1.13	34.46	4.82	47.59	1.06	48.71	0.94
f_sushi	43.55	1.69	43.77	1.65	45.39	1.37	33.96	5.11	45.03	1.43	46.50	1.21
f_tomates	41.45	2.16	44.14	1.58	44.35	1.55	37.40	3.44	44.36	1.54	46.58	1.20
feathers	35.30	4.38	36.54	3.80	40.19	2.50	31.42	6.85	41.82	2.07	44.02	1.61
flowers	44.45	1.53	40.13	2.51	44.79	1.47	32.41	6.11	45.44	1.36	46.91	1.15
g_tiles	38.22	3.13	36.81	3.68	38.75	2.94	32.70	5.91	38.16	3.15	39.58	2.68
hairs	45.79	1.31	42.81	1.85	44.88	1.45	33.16	5.61	45.64	1.33	46.87	1.16
j_beans	37.66	3.34	37.82	3.28	38.92	2.89	29.56	8.49	40.02	2.54	40.81	2.32
oil_paint	39.88	2.58	40.28	2.47	41.26	2.21	33.64	5.30	41.15	2.23	42.79	1.85
paints	38.87	2.90	30.53	7.58	35.90	4.09	31.11	7.09	39.50	2.70	41.03	2.26
p_face	42.94	1.82	41.58	2.13	42.75	1.86	38.59	3.00	42.97	1.81	44.92	1.45
pompoms	43.66	1.67	41.35	2.18	41.56	2.13	31.55	6.75	45.63	1.33	47.88	1.03
r_apples	50.31	0.78	47.76	1.04	49.50	0.85	33.32	5.51	50.19	0.79	51.75	0.66
r_peppers	46.73	1.18	46.25	1.24	47.71	1.05	33.51	5.38	48.64	0.94	50.65	0.75
sponges	45.69	1.32	45.21	1.40	45.00	1.43	36.02	4.03	44.58	1.50	47.14	1.12
s_toys	44.47	1.52	42.01	2.02	43.68	1.67	28.67	9.39	45.01	1.43	45.64	1.33
superball	45.78	1.31	43.35	1.73	45.91	1.29	35.86	4.11	46.09	1.27	47.97	1.02
th_spools	43.62	1.68	43.55	1.69	44.31	1.55	32.98	5.72	44.52	1.52	46.38	1.22
watercol	39.77	2.62	39.16	2.81	40.64	2.37	27.37	10.91	40.78	2.33	43.01	1.80
Average	43.11	2.01	41.83	2.34	43.53	1.89	33.64	5.69	44.15	1.75	45.91	1.42
Std.dev	4.13	1.03	4.09	1.38	3.83	0.94	3.24	2.22	3.79	0.88	3.66	0.67
S=16
Method	CNMF		MF		SNNMF		G-SOMP+		BSR		Proposed NSSR
balloons	46.57	1.20	44.75	1.48	45.04	1.43	35.27	4.40	46.35	1.23	48.36	0.97
beads	33.95	5.12	32.33	6.16	33.13	5.62	29.18	8.86	33.16	5.61	35.84	4.12
cd	33.21	5.58	31.97	6.42	33.68	5.28	26.38	12.23	34.78	4.65	36.02	4.03
chart_toy	38.66	2.98	39.39	2.73	39.17	2.81	33.46	5.42	41.35	2.18	43.04	1.80
clay	46.52	1.20	43.46	1.71	43.91	1.63	36.42	3.85	45.66	1.33	47.45	1.08
cloth	35.06	4.51	33.27	5.53	33.82	5.20	31.52	6.77	35.46	4.30	37.58	3.37
eg_statue	46.71	1.18	47.22	1.11	47.27	1.10	35.58	4.24	48.44	0.96	48.44	0.96
face	45.15	1.41	43.47	1.71	44.49	1.52	38.30	3.10	44.39	1.54	45.23	1.40
f_beers	44.76	1.47	44.68	1.49	45.17	1.41	35.08	4.49	45.23	1.40	45.98	1.28
f_food	41.85	2.06	39.21	2.79	42.25	1.97	34.31	4.91	43.04	1.80	45.48	1.36
f_lemon_s	42.14	1.99	37.30	3.48	42.30	1.96	35.73	4.17	43.67	1.67	45.20	1.40
f_lemons	45.19	1.40	46.73	1.18	46.30	1.23	37.62	3.35	46.56	1.20	49.56	0.85
f_peppers	39.52	2.69	44.11	1.59	42.07	2.01	33.76	5.23	44.30	1.55	46.84	1.16
f_strawbe	44.57	1.51	41.94	2.04	45.59	1.34	37.62	3.35	46.25	1.24	47.69	1.05
f_sushi	41.58	2.13	41.38	2.17	42.08	2.01	33.84	5.18	43.22	1.76	45.30	1.38
f_tomates	39.76	2.62	44.43	1.53	41.80	2.07	34.49	4.81	43.40	1.72	46.13	1.26
feathers	40.48	2.41	38.45	3.05	37.82	3.28	33.67	5.28	39.90	2.58	42.09	2.00
flowers	43.91	1.63	39.06	2.84	40.87	2.31	33.02	5.69	43.22	1.76	45.28	1.39
g_tiles	37.80	3.28	38.43	3.06	37.55	3.38	33.94	5.12	37.47	3.41	38.18	3.14
hairs	40.67	2.36	43.61	1.68	42.74	1.86	36.29	3.91	44.44	1.53	45.71	1.32
j_beans	35.75	4.16	32.55	6.01	35.87	4.10	28.71	9.36	37.84	3.27	39.19	2.80
oil_paint	39.03	2.85	39.56	2.68	39.98	2.56	34.09	5.04	40.51	2.40	41.96	2.04
paints	37.83	3.27	37.39	3.44	37.31	3.48	32.56	6.01	38.45	3.05	39.38	2.74
p_face	40.72	2.35	40.65	2.37	39.92	2.57	38.44	3.05	41.63	2.11	42.64	1.88
pompoms	40.69	2.36	38.23	3.13	40.89	2.30	33.71	5.26	41.92	2.04	45.05	1.43
r_apples	47.81	1.04	44.82	1.46	47.08	1.13	36.73	3.72	48.54	0.95	50.44	0.77
r_peppers	44.32	1.55	42.01	2.02	45.45	1.36	36.49	3.82	45.87	1.30	49.21	0.88
sponges	44.93	1.45	42.41	1.93	43.08	1.79	33.75	5.24	42.63	1.88	45.90	1.29
s_toys	41.80	2.07	39.92	2.58	41.44	2.16	31.65	6.67	42.11	2.00	42.51	1.91
superball	43.15	1.77	41.98	2.03	41.82	2.07	34.38	4.87	44.14	1.58	45.91	1.29
th_spools	41.86	2.06	40.33	2.45	39.53	2.69	31.72	6.61	42.60	1.89	44.58	1.50
watercol	38.74	2.95	38.62	2.99	39.27	2.77	30.30	7.79	39.83	2.60	41.34	2.19
Average	41.40	2.39	40.43	2.71	41.21	2.45	34.00	5.37	42.39	2.14	44.17	1.75
Std.dev	3.76	1.13	3.96	1.41	3.76	1.18	2.75	1.94	3.72	1.07	3.83	0.88
S=32
Methods	CNMF		MF		SNNMF		G-SOMP+		BSR		Proposed NSSR
balloons	44.78	1.47	41.92	2.04	40.55	2.39	35.25	4.41	42.96	1.81	45.55	1.35
beads	33.22	5.57	31.38	6.88	30.05	8.02	29.05	8.99	31.14	7.07	33.31	5.51
cd	30.81	7.34	31.10	7.10	31.34	6.91	28.23	9.88	30.93	7.25	33.11	5.64
chart_toy	37.87	3.26	38.29	3.10	38.06	3.19	32.70	5.91	39.01	2.86	42.06	2.01
clay	44.80	1.47	42.17	1.99	42.34	1.95	39.29	2.77	42.53	1.90	46.29	1.24
cloth	34.57	4.77	35.50	4.28	32.63	5.96	30.00	8.06	34.72	4.68	36.23	3.94
eg_statue	45.06	1.42	46.57	1.20	46.49	1.21	38.36	3.08	47.24	1.11	47.64	1.06
face	44.40	1.54	42.42	1.93	42.43	1.93	35.28	4.39	43.55	1.69	44.08	1.60
f_beers	40.83	2.32	43.04	1.80	42.72	1.86	35.95	4.07	41.41	2.17	44.35	1.55
f_food	38.76	2.94	38.68	2.97	36.75	3.71	31.20	7.03	39.68	2.65	42.79	1.85
f_lemon_s	40.09	2.52	38.90	2.89	37.31	3.47	29.95	8.11	40.78	2.33	43.57	1.69
f_lemons	42.66	1.88	45.49	1.36	44.17	1.58	37.35	3.46	45.43	1.36	48.56	0.95
f_peppers	37.66	3.34	41.81	2.07	40.28	2.47	31.62	6.69	42.13	2.00	44.86	1.46
f_strawbe	43.07	1.79	41.28	2.20	43.16	1.77	33.69	5.27	44.24	1.56	46.46	1.21
f_sushi	37.18	3.53	40.84	2.31	39.24	2.78	32.78	5.85	39.05	2.84	42.92	1.82
f_tomates	39.73	2.63	42.08	2.01	41.18	2.23	34.30	4.92	42.56	1.90	45.16	1.41
feathers	38.37	3.08	38.14	3.16	34.14	5.01	32.67	5.93	36.96	3.62	39.81	2.61
flowers	42.20	1.98	39.89	2.58	37.54	3.38	32.98	5.72	40.53	2.40	42.55	1.90
g_tiles	36.96	3.62	37.04	3.58	35.40	4.33	28.98	9.06	36.20	3.95	36.49	3.82
hairs	39.96	2.56	41.46	2.15	41.62	2.12	35.26	4.40	43.02	1.80	44.35	1.55
j_beans	33.96	5.11	33.25	5.54	32.85	5.81	28.77	9.29	34.13	5.01	37.10	3.56
oil_paint	37.29	3.48	38.90	2.90	38.83	2.92	32.72	5.90	39.57	2.68	40.93	2.29
paints	36.54	3.80	34.18	4.99	35.83	4.12	30.13	7.94	35.95	4.06	36.91	3.64
p_face	40.07	2.53	41.58	2.13	41.66	2.11	38.68	2.97	40.96	2.28	41.80	2.07
pompoms	38.26	3.12	36.04	4.02	36.38	3.87	29.98	8.08	36.27	3.92	42.15	1.99
r_apples	45.51	1.35	44.57	1.51	42.60	1.89	36.83	3.68	45.79	1.31	47.42	1.09
r_peppers	41.28	2.20	43.64	1.68	40.87	2.31	36.44	3.84	43.94	1.62	47.01	1.14
sponges	42.81	1.85	40.10	2.52	39.81	2.61	35.42	4.32	39.37	2.74	43.93	1.62
s_toys	39.31	2.76	35.73	4.17	38.22	3.13	29.21	8.83	37.72	3.31	38.07	3.18
superball	40.37	2.44	38.67	2.97	38.93	2.89	34.75	4.67	41.14	2.24	44.19	1.57
th_spools	38.62	2.99	37.05	3.58	38.30	3.10	31.85	6.52	39.04	2.85	41.97	2.03
watercol	37.82	3.28	38.03	3.20	37.75	3.30	27.41	10.87	38.31	3.10	40.76	2.34
Average	39.53	2.93	39.37	3.03	38.73	3.26	33.03	6.09	39.88	2.88	42.26	2.21
Std.dev	3.55	1.30	3.76	1.44	3.79	1.57	3.27	2.21	3.91	1.46	4.01	1.19

Table 2 PSNR and RMSE results of the test methods on the Harvard dataset (Uniform blur kernel)

S=8
Method	CNMF		MF		SNNMF		G-SOMP+		BSR		Proposed NSSR
	PSNR	RMSE	PSNR	RMSE	PSNR	RMSE	PSNR	RMSE	PSNR	RMSE	PSNR	RMSE
img1	46.20	1.25	46.01	1.28	46.09	1.26	44.93	1.45	46.38	1.22	46.30	1.23
img2	44.98	1.44	42.56	1.90	44.26	1.56	39.08	2.83	45.46	1.36	45.17	1.41
imga1	43.20	1.76	43.51	1.70	43.32	1.74	40.29	2.47	43.67	1.67	43.69	1.67
imga2	50.76	0.74	50.22	0.79	50.74	0.74	48.92	0.91	50.87	0.73	50.90	0.73
imga5	50.70	0.74	50.15	0.79	49.99	0.81	41.41	2.17	50.74	0.74	50.87	0.73
imga6	41.74	2.09	43.35	1.73	42.54	1.90	34.25	4.95	41.51	2.14	44.07	1.60
imga7	45.70	1.32	45.77	1.31	45.82	1.31	42.18	1.98	45.59	1.34	45.82	1.30
imgb0	44.06	1.60	45.01	1.43	45.58	1.34	43.15	1.77	44.11	1.59	46.03	1.27
imgb1	40.30	2.46	40.46	2.42	40.49	2.41	27.71	10.50	40.49	2.41	40.46	2.42
imgb2	44.84	1.46	43.78	1.65	44.39	1.54	37.78	3.29	44.57	1.51	45.06	1.42
imgb3	44.72	1.48	43.31	1.74	44.66	1.49	34.61	4.75	45.05	1.43	45.53	1.35
imgb4	38.10	3.17	37.65	3.34	38.64	2.98	36.25