Deep and adaptive feature extraction attention network for single image super-resolution

Single image super-resolution (SISR) has been revolutionized by convolutional neural networks (CNN). However, existing SISR algorithms have feature extraction and adaptive adjustment limitations, leading to information duplication and unsatisfactory image reconstruction. In this paper, we propose a deep and adaptive feature extraction attention network (DAAN), which first fully extracts shallow features and then adaptively captures precise and fine-scale features by a deep feature extraction block (DFEB). It includes multi-dimensional feature extraction blocks (MFEBs) that combine large kernel and dynamic convolution layers to improve large-scale information utilization effectively. Finally, an enhanced spatial attention block (ESAB) to further selectively reinforce the transmission of details. A large number of experimental results show that our proposed model reconstruction performance is superior to existing classical methods. This paper shows the architecture of the proposed deep and adaptive feature extraction attention network (DAAN). SFEB, DFEB, and ESAB stand for the shallow feature extraction block, the deep feature extraction block, and the enhanced spatial attention block, respectively.image

Automated summary

This paper proposes a deep and adaptive feature extraction attention network (DAAN) for single image super-resolution (SISR) task. The model utilizes multi-dimensional feature extraction blocks and enhanced spatial attention block to accurately capture and utilize image features at various scales.