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.

Schematic diagram of UMFFA structure.

More »

Fig 1 Expand

Fig 2.

Composition of the RDAB and Basic Block.

More »

Fig 2 Expand

Fig 3.

Multi-path channel attention and pixel attention modules.

More »

Fig 3 Expand

Fig 4.

Input and pixel channel attention weight.

(a) Input and (b) Pixel channel weight.

More »

Fig 4 Expand

Fig 5.

Multi-path channel attention weight.

More »

Fig 5 Expand

Fig 6.

Highway dataset.

(a) Ground truth and (b) Hazy image.

More »

Fig 6 Expand

Table 1.

Training platform and related parameters.

More »

Table 1 Expand

Table 2.

Comparison of the performance of different methods.

More »

Table 2 Expand

Table 3.

Ablation test setup.

More »

Table 3 Expand

Fig 7.

Changes in performance metrics of different methods in ablation tests.

(a) PSNR and (b) SSIM.

More »

Fig 7 Expand

Table 4.

Comparison of ablation test performance metrics on the Highway data set (average on last 20 results).

More »

Table 4 Expand

Fig 8.

Effect of different β on the performance metrics PSNR/SSIM.

(a) PSNR and (b) SSIM.

More »

Fig 8 Expand

Fig 9.

The effect of β on the performance metrics L∞ error.

More »

Fig 9 Expand

Table 5.

Influence of β on performance metrics.

More »

Table 5 Expand

Table 6.

Comparison on Highway dataset with multi-channel pooling.

More »

Table 6 Expand

Table 7.

Comparison results with multi-channel pooling on the I-Haze dataset.

More »

Table 7 Expand

Fig 10.

Image 109 from dataset I-Haze.

More »

Fig 10 Expand

Fig 11.

Image 132 from dataset I-Haze.

More »

Fig 11 Expand

Fig 12.

Image 21 from dataset Highway.

More »

Fig 12 Expand

Fig 13.

Image 28 from dataset Highway.

More »

Fig 13 Expand