Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

Retinex schematic diagram.

More »

Fig 1 Expand

Fig 2.

Overall network structure.

More »

Fig 2 Expand

Fig 3.

Structure of the decomposition network.

More »

Fig 3 Expand

Fig 4.

Results of adding SSIM loss function to KinD.

More »

Fig 4 Expand

Fig 5.

Comparison of ReLU function and GELU function in decomposition network.

More »

Fig 5 Expand

Fig 6.

Structure of the reflective component denoising network.

More »

Fig 6 Expand

Fig 7.

Results of adding CA attention to Unet3+.

More »

Fig 7 Expand

Fig 8.

Structure of the illumination component enhancement network.

More »

Fig 8 Expand

Fig 9.

Comparison results of different iteration times n.

More »

Fig 9 Expand

Table 1.

Comparison results of different iteration times n.

More »

Table 1 Expand

Fig 10.

Comparison results of different methods on LOL test set.

More »

Fig 10 Expand

Fig 11.

Comparison results of different methods on VE-LOL-L test set.

More »

Fig 11 Expand

Fig 12.

Comparison results of different methods on DICM test set.

More »

Fig 12 Expand

Fig 13.

Comparison results of different methods on MEF test set.

More »

Fig 13 Expand

Fig 14.

Comparison results of different methods on SID test set.

More »

Fig 14 Expand

Fig 15.

Comparison results of different methods on ELD test set.

More »

Fig 15 Expand

Table 2.

Comparison results of different methods on LOL dataset.

More »

Table 2 Expand

Table 3.

Comparison results of different methods on VE-LOL-L dataset.

More »

Table 3 Expand

Table 4.

Comparison results of different methods on SID dataset.

More »

Table 4 Expand

Table 5.

Comparison results of different methods on ELD dataset.

More »

Table 5 Expand

Table 6.

Comparison results of different methods on DICM dataset.

More »

Table 6 Expand

Table 7.

Comparison results of different methods on MEF dataset.

More »

Table 7 Expand

Fig 16.

Ablation studies on the framework.

‘w/o Denois.’ denotes our method without reflective component denoising network. ‘w/o Enhance.’ denotes our method without illumination component enhancement network.

More »

Fig 16 Expand

Table 8.

Comparison of ablation results for different modules.

More »

Table 8 Expand