Table 6 Quantitative results on widely-used benchmarks. The best results are marked in bold. Higher SSIM values reflect improved performance.

From: A two-stage multi-scale attention-based network for weakly supervised cataract fundus image enhancement

Method

SSIM

TLLR42

0.50

LLIE43

0.55

HIEA44

0.65

RPCA45

0.78

Ours

0.82