Table 3 Evaluation of competitive SISR and STISR models on TextZoom datasets
From: BCSR: toward arbitrarily oriented text image super-resolution via adaptive Bezier curve network
Approach | PSNR/dB | SSIM | ||||||
|---|---|---|---|---|---|---|---|---|
Simple | Medium | Hard | Average | Simple | Medium | Hard | Average | |
Bicubic | 22.35 | 18.98 | 19.39 | 20.35 | 0.7884 | 0.6254 | 0.6592 | 0.6961 |
SRCNN [3] | 23.48 | 19.06 | 19.34 | 20.78 | 0.8379 | 0.6323 | 0.6791 | 0.7227 |
SRResnet [7] | 24.36 | 18.88 | 19.29 | 21.03 | 0.8681 | 0.6406 | 0.6911 | 0.7403 |
HAN [46] | 23.30 | 19.02 | 20.16 | 20.95 | 0.8691 | 0.6537 | 0.7387 | 0.7596 |
TSRN [9] | 25.07 | 18.86 | 19.71 | 21.42 | 0.8897 | 0.6676 | 0.7302 | 0.7690 |
TBSRN [12] | 23.46 | 19.17 | 19.68 | 20.91 | 0.8729 | 0.6455 | 0.7452 | 0.7603 |
PCAN [47] | 24.57 | 19.14 | 20.26 | 21.49 | 0.8830 | 0.6781 | 0.7475 | 0.7752 |
TPGSR [12] | 23.73 | 18.68 | 20.06 | 20.97 | 0.8805 | 0.6738 | 0.7440 | 0.7719 |
TPGSR-3 [12] | 24.35 | 18.73 | 19.93 | 21.18 | 0.8860 | 0.6784 | 0.7487 | 0.7774 |
Ours | 25.35 | 19.02 | 20.93 | 21.67 | 0.8901 | 0.6763 | 0.7507 | 0.7991 |