Figure 2

The overall architecture of AFDNet. The input is decomposed into five-scale Laplacian pyramids by decomposition, and feature fusion is performed by channel splicing in the encoding branch. In the decoding branch, the AFD model is used instead of the traditional skip connection method to gradually fuse the frequency features extracted by the encoding branch with the features extracted by other branches. The residual map output by the network is added to the result of multiplying the input image by \(\alpha \) to obtain the image enhancement result, where \(\alpha \) is a learnable parameter.