Table 1 Quantitative results of three supervised metrics (PSNR, SSIM, and LPIPS) and four no-reference metrics (NIQE, NIMA, MUSIQ, and ILNIQE) on the MIT dataset.
From: CUI-Net: a correcting uneven illumination net for low-light image enhancement
Method | SSIM\(\uparrow\) | PSNR\(\uparrow\) | LPIPS\(\downarrow\) | NIQE\(\downarrow\) | NIMA\(\uparrow\) | MUSIQ\(\uparrow\) | ILNIQE\(\downarrow\) |
|---|---|---|---|---|---|---|---|
EnlightGAN | 0.7979 | 16.5871 | 0.204 | 4.1572 | 3.3962 | 55.4027 | 34.6982 |
KinD | 0.8037 | 16.8844 | 0.1982 | 4.2655 | 3.8035 | 49.2749 | 33.4907 |
ZeroDCE | 0.7755 | 16.0836 | 0.2261 | 4.8881 | 3.2382 | 58.8717 | 37.6914 |
ZeroDCE++ | 0.4356 | 6.6687 | 0.5018 | 5.5502 | 3.3837 | 47.0083 | 36.7629 |
RUAS | 0.8301 | 18.3021 | 0.2086 | 4.7324 | 3.5027 | 54.7674 | 35.9107 |
SCI | 0.8354 | 18.42 | 0.1752 | 4.4377 | 3.4981 | 57.8329 | 34.0613 |
Uretinex | 0.7694 | 16.166 | 0.2135 | 4.5749 | 3.6984 | 60.7205 | 34.9065 |
CUI | 0.8305 | 19.328 | 0.1736 | 4.1532 | 3.4726 | 56.9714 | 31.9151 |
