A Two-Stage Attentive Network for Single Image Super-Resolution

Recently, deep convolutional neural networks (CNNs) have been widely explored in single image super-resolution (SISR) and contribute remarkable progress. However, most of the existing CNNs-based SISR methods do not adequately explore contextual information feature extraction stage pay little attention to final high-resolution (HR) reconstruction step, hence hindering desired SR performance. To address above two issues, this paper, we propose a two-stage attentive network (TSAN) for accurate coarse-to-fine manner. Specifically, design novel multi-context block (MCAB) make focus on more informative features. Moreover, present an essential refined (RAB) which could useful cues HR space reconstructing fine-detailed image. Extensive evaluations four benchmark datasets demonstrate efficacy our proposed TSAN terms quantitative metrics visual effects. Code is available at https://github.com/Jee-King/TSAN.