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.

The image obtained by Retinex-Net has well-preserved color details, but there is noise; the image obtained by KinD and KinD++ has good denoising effect, but the details are blurred.

More »

Fig 1 Expand

Fig 2.

The framework of the proposed model.

More »

Fig 2 Expand

Fig 3.

The framework of the proposed model.

More »

Fig 3 Expand

Fig 4.

Multi-branch dilation convolution module.

More »

Fig 4 Expand

Fig 5.

U-Net feature learning module.

More »

Fig 5 Expand

Fig 6.

Adaptive iterative learning module.

More »

Fig 6 Expand

Fig 7.

Layer-by-layer denoising decomposition module.

More »

Fig 7 Expand

Fig 8.

Reflection component denoising module.

More »

Fig 8 Expand

Fig 9.

Subjective visualization of various methods on the LOL dataset.

More »

Fig 9 Expand

Table 1.

Objective evaluation results of different algorithms on LOL datasets.

More »

Table 1 Expand

Fig 10.

Subjective visualization of various methods on the LOLv2-Real dataset.

More »

Fig 10 Expand

Table 2.

Objective evaluation results of different algorithms on LOL-v2-Real datasets.

More »

Table 2 Expand

Fig 11.

Subjective visualization of various methods on the DICM dataset.

More »

Fig 11 Expand

Fig 12.

Subjective visualization of various methods on the MEF dataset.

More »

Fig 12 Expand

Fig 13.

Subjective visualization of various methods on the LIME dataset.

More »

Fig 13 Expand

Fig 14.

Subjective visualization of various methods on the NPE dataset.

More »

Fig 14 Expand

Fig 15.

Subjective visualization of various methods on the Real-world dataset.

More »

Fig 15 Expand

Table 3.

Objective evaluation results of different algorithms on DICM, LIME, MEF, NPE, Real-world datasets.

More »

Table 3 Expand

Fig 16.

Subjective visualization of network module ablation experiments.

More »

Fig 16 Expand

Table 4.

Objective evaluation results of network module ablation experiments.

More »

Table 4 Expand

Fig 17.

Subjective visualization of the loss ablation experiment.

More »

Fig 17 Expand

Table 5.

Results of objective evaluation of loss ablation experiments.

More »

Table 5 Expand

Fig 18.

Multibranch dilation convolution modules ablation experiment subjective visual map.

More »

Fig 18 Expand

Table 6.

Objective evaluation results of ablation experiments for multibranch dilation convolution module.

More »

Table 6 Expand

Fig 19.

The visual effect of our method in enhancing images with both very dark and exposed areas.

More »

Fig 19 Expand