Research Article

Generative Adversarial Network-Based Edge-Preserving Superresolution Reconstruction of Infrared Images

Table 2

Method comparison: quantitative results of the SRCNN, ESPCN, SRGAN, ESRGAN, and ESRGAN+ methods and the proposed method on the Itir_v1_0 dataset.

CCPSNR (dB)SSIMVIFUIQITIME (s)

SRCNN0.793720.24600.89660.70790.87462.5706
ESPCN0.846422.17080.91850.81940.98771.0020
SRGAN0.815222.67320.91540.79440.86100.6642
ESRGAN0.914630.32050.96080.77520.91660.0937
ESRGAN+0.954734.10240.98440.84970.95410.2558
Ours0.996235.28650.99430.90640.99360.1059