Image moire noise removal method based on multi-scale dynamic feature aggregation

The invention discloses an image moire noise removal method based on multi-scale dynamic feature aggregation, which comprises the following steps of: respectively constructing a residual dense block, a scale feature extraction and fusion module and a main-bypass dynamic coding module, fusing the residual dense block and the scale feature extraction and fusion module into a combined module, and performing jump connection on the combined module, the main-bypass dynamic coding module structure adopts residual connection, and the combination module and the main-bypass dynamic coding module are coupled according to a preset mode to form a deep convolutional neural network. The beneficial effects of the invention are that the multi-scale feature extraction and fusion module is provided for solving the problem of insufficient multi-scale feature fusion of moire noise, and the multi-scale feature extraction and fusion module is used for better utilizing the multi-scale feature information and better realizing the com