The explanation in the paper is wrong.

[kimjy1211]

In the line 98 of AECRNet.py

The authors define the DehazeBlock only once.

So all DehazeBlocks share parameters.

This is different from the description in the paper.

[hrishikeshps94]

It seems like to adhere to the number of parameters(2.61M) shown in the paper weights should be shared or else it would be very high number nearly 8M. The description in the paper seems to be a bit misleading.