基于动态注意力网络的图像超分辨率重建
|
|
赵小强,王泽,宋昭漾,蒋红梅
|
Image super-resolution reconstruction based on dynamic attention network
|
|
Xiao-qiang ZHAO,Ze WANG,Zhao-yang SONG,Hong-mei JIANG
|
|
| 表 1 不同SR算法在放大倍数为2、3、4时的平均PSNR与SSIM |
| Tab.1 Average PSNR and SSIM for different SR algorithms at magnifications of 2, 3 and 4 |
|
| 方法 | 倍数 | 参数量/K | PSNR(dB)/SSIM | | Set5 | Set14 | BSD100 | Urban100 | Manga109 | | Bicubic | 2 | — | 33.68/0.9304 | 30.24/0.8691 | 29.56/0.8435 | 26.88/0.8405 | 30.80/0.9339 | | IMDN | 694 | 38.00/0.9605 | 33.63/0.9177 | 32.19/0.8996 | 32.17/0.9283 | 38.88/0.977 4 | | MemNet | 677 | 37.78/0.9597 | 33.28/0.9142 | 32.08/0.8978 | 31.31/0.9195 | 37.72/0.9740 | | CARN | 1592 | 37.76/0.9590 | 33.52/0.9166 | 32.09/0.8978 | 31.92/0.9256 | 38.36/0.9765 | | EDSR-baseline | 1370 | 37.99/0.9604 | 33.57/0.9175 | 32.16/0.8994 | 31.98/0.9272 | 38.45/0.9770 | | SRMDNF | 1513 | 37.79/0.9600 | 33.32/0.9150 | 32.05/0.8980 | 31.33/0.9200 | — | | SeaNet-baseline | 2102 | 37.99/0.9607 | 33.60/0.9174 | 32.18/0.8995 | 32.08/0.9276 | 38.48/0.9768 | | Cross-SRN | 1296 | 38.03/0.9606 | 33.62/0.9180 | 32.19/0.8997 | 32.28/0.9290 | 38.75/0.9773 | | DAN(本研究) | 1298 | 38.04/0.9608 | 33.64/0.9180 | 32.20/0.8998 | 32.26/0.9296 | 38.72/0.9773 | | Bicubic | 3 | — | 30.93/0.8682 | 27.55/0.7742 | 27.21/0.7385 | 24.46/0.7349 | 26.95/0.8556 | | IMDN | 703 | 34.36/0.9270 | 30.32/0.8417 | 29.09/0.8046 | 28.17/0.8519 | 33.61/0.9445 | | MemNet] | 677 | 34.09/0.9248 | 30.00/0.8350 | 28.96/0.8001 | 27.56/0.8376 | 32.51/0.9369 | | CARN | 1592 | 34.29/0.9255 | 30.29/0.8407 | 29.06/0.8034 | 28.06/0.8493 | 33.50/0.9440 | | EDSR-baseline | 1500 | 34.37/0.9270 | 30.28/0.8417 | 29.09/0.8052 | 28.15/0.8527 | 33.49/0.9438 | | SRMDNF | 1530 | 34.12/0.9250 | 30.04/0.8370 | 28.97/0.8030 | 27.57/0.8400 | — | | SeaNet-baseline | 2471 | 34.36/0.9280 | 30.34/0.8428 | 29.09/0.8053 | 28.17/0.8527 | 33.40/0.9444 | | Cross-SRN | 1296 | 34.43/0.9275 | 30.33/0.8417 | 29.09/0.8050 | 28.23/0.8535 | 33.65/0.9448 | | DAN(本研究) | 1326 | 34.42/0.9274 | 30.38/0.8429 | 29.10/0.8052 | 28.24/0.8542 | 33.63/0.9446 | | Bicubic | 4 | — | 28.42/0.8104 | 26.00/0.7027 | 26.96/0.6675 | 23.14/0.6577 | 24.80/0.7866 | | IMDN | 715 | 32.21/0.8948 | 28.58/0.7811 | 27.56/0.7353 | 26.04/0.7838 | 30.45/0.9075 | | MemNet | 677 | 31.74/0.8893 | 28.26/0.7723 | 27.40/0.7281 | 25.50/0.7630 | 29.42/0.8942 | | CARN | 1592 | 32.13/0.8937 | 28.60/0.7806 | 27.58/0.7349 | 26.07/0.7837 | 30.47/0.9087 | | EDSR-baseline | 1500 | 32.09/0.8938 | 28.58/0.7813 | 27.57/0.7357 | 26.04/0.7849 | 30.45/0.9082 | | SRMDNF | 1555 | 31.96/0.8930 | 28.35/0.7770 | 27.49/0.7340 | 25.68/0.7730 | — | | SeaNet-baseline | 2397 | 32.18/0.8948 | 28.61/0.7822 | 27.57/0.7359 | 26.05/0.7896 | 30.44/0.9088 | | Cross-SRN | 1296 | 32.24/0.8954 | 28.59/0.7817 | 27.58/0.7364 | 26.16/0.7881 | 30.53/0.9081 | | DAN(本研究) | 1337 | 32.32/0.8962 | 28.68/0.7841 | 27.62/0.7381 | 26.31/0.7936 | 30.68/0.9106 |
|
|
|