Recently, deep convolutional neural networks (CNNs) have achieved excellent performance on image super-resolution (SR). However, the majority of the deep CNN-based super-resolution models struggle to capture global context due to their limited receptive fields and do not fully utilize intermediate features, which limits their performance and application. To address this issue, we propose an image super-resolution reconstruction network (DBFA) based on dual-branch feature interaction attention mechanism, aimed at capturing global context and multi-scale local features. DBFA uses the Transformer...
