Research on Lightweight Super-resolution Reconstruction Algorithm Based on Progressive Feature Fusion Convolutional Network
Most super-resolution reconstruction algorithms extract more feature details through extended convolutional neural networks,which can easily lead to an increase in computational complexity and model parameter quantity.Therefore,this arti-cle proposes a lightweight super-resolution algorithm for progressive feature fusion convolutional networks,which mainly ag-gregates multi-scale features in a progressive manner and utilizes multi-scale pixel attention mechanism to construct a concise and efficient up-sampling module,ensuring network efficiency and lightweight model design.On this basis,a training strategy based on cosine annealing learning is also proposed to improve the quality of restored images without changing the model struc-ture.
万方数据
维普
