Skip to main content

Table 1 PSNR/SSIM values of state-of-the-art SR methods. The bold number indicates the best performance

From: Single-frame super-resolution for remote sensing images based on improved deep recursive residual network

Scene Scale Bicubic SRCNN FSRCNN DRCN VDSR EDSR IDRRN
Airplane ×2 31.43/0.8999 33.78/0.9270 34.05/0.9287 34.19/0.9322 34.78/0.9347 35.01/0.9354 35.20/0.9493
×3 29.12/0.8211 30.53/0.8439 31.12/0.8502 31.25/0.8667 31.41/0.8961 31.37/0.8863 31.78/0.8997
×4 27.03/0.7529 27.99/0.7718 28.24/0.7945 28.97/0.7940 29.26/0.8242 29.39/0.8271 29.42/0.8288
Bridge ×2 27.94/0.8813 28.50/0.9003 28.89/0.9039 29.02/0.9024 29.50/0.9168 29.42/0.9076 30.03/0.9194
×3 25.89/0.7714 27.01/0.7948 27.52/0.8109 27.99/0.8072 28.33/0.8222 28.48/0.8115 28.49/0.8258
×4 24.33/0.7253 25.12/0.7501 25.49/0.7592 25.71/0.7663 26.05/0.7620 25.47/0.7708 26.44/0.7854
Harbor ×2 21.16/0.8944 23.63/0.9058 23.97/0.9139 24.09/0.9243 26.05/0.9440 26.31/0.9502 26.35/0.9593
×3 18.49/0.7467 20.27/0.7580 20.81/0.7789 21.13/0.7941 22.16/0.8102 22.39/0.8003 22.48/0.8115
×4 16.93/0.5465 18.50/0.6019 18.84/0.6463 19.01/0.6740 19.36/0.7509 19.33/0.7482 19.42/0.7485
Inter-section ×2 19.84/0.7444 20.95/0.8039 21.28/0.8176 21.13/0.7916 23.27/0.8513 22.19/0.8240 23.86/0.8532
×3 17.49/0.5894 18.30/0.6189 19.52/0.6540 20.01/0.6693 20.12/0.7578 19.64/0.7602 20.16/0.7733
×4 14.47/0.4413 15.12/0.4914 15.36/0.4805 14.83/0.5301 15.02/0.5016 15.96/0.5633 16.43/0.5605
Parking_lot ×2 24.91/0.8081 26.02/0.8192 26.99/0.8206 27.38/0.8243 28.01/0.8444 27.94/0.8135 28.03/0.8487
×3 22.47/0.6176 22.96/0.6895 23.53/0.6543 23.97/0.7014 24.81/0.7288 25.02/0.7355 25.28/0.7356
×4 21.04/0.5543 21.77/0.5720 22.84/0.5782 23.15/0.5924 22.98/0.6013 23.55/0.5947 23.78/0.6172