Lightweight super-resolution reconstruction via progressive multi-path feature fusion and attention mechanism
In order to further explore the possibility of applying super-resolution methods on computing and storage re-source-constrained devices,this study focuses on the application of deep convolutional neural network technology in single-image super-resolution,especially how to improve the performance of the network without significantly increas-ing the network size.In this paper,a novel lightweight single image super resolution(SISR)method via progressive multi-path feature fusion and attention mechanism(MPFFA)is proposed.MPFFA includes a multi-path FPF module,which can progressively guide and calibrate the learning of the following features through multiple paths.MPFFA also includes a multi-path feature attention mechanism(FAM),which can improve the utilization rate of feature information and the ability of feature expression by splicing multi-path features with weights.The experimental result shows that MPFFA significantly outperforms other representative methods,thus achieves a better balance between model complex-ity and performance.The proposed model can be better applied to computing and resource-constrained devices.
万方数据
维普
