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

Abstract

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 in the feature extraction stage and pay little attention to the final high-resolution (HR) image reconstruction step, hence hindering the desired SR performance. To address the above two issues, in this paper, we propose a two-stage attentive network (TSAN) for accurate SISR in a coarse-to-fine manner. Specifically, we design a novel multi-context attentive block (MCAB) to make the network focus on more informative contextual features. Moreover, we present an essential refined attention block (RAB) which could explore useful cues in HR space for reconstructing fine-detailed HR image. Extensive evaluations on four benchmark datasets demonstrate the efficacy of our proposed TSAN in terms of quantitative metrics and visual effects. Code is available at https://github.com/Jee-King/TSAN.

References in corpus (7)

• Denoising Prior Driven Deep Neural Network for Image Restoration
• Diversified Visual Attention Networks for Fine-Grained Object Classification
• Residual Non-local Attention Networks for Image Restoration
• An Energy-Efficient FPGA-based Deconvolutional Neural Networks Accelerator for Single Image Super-Resolution
• DRFN: Deep Recurrent Fusion Network for Single-Image Super-Resolution with Large Factors
• Accurate and Lightweight Image Super-Resolution with Model-Guided Deep Unfolding Network
• Is Second-order Information Helpful for Large-scale Visual Recognition?

Cited by in corpus (9)

• Progressive Glass Segmentation
• Super-resolution Reconstruction of Single Image for Latent features
• Neuromorphic Imaging with Super-Resolution
• Dual Graph Convolutional Networks with Transformer and Curriculum Learning for Image Captioning
• CANet: A Context-Aware Network for Shadow Removal
• Multi-Level Attentive Convoluntional Neural Network for Crowd Counting
• Feedback Pyramid Attention Networks for Single Image Super-Resolution
• Luminance Attentive Networks for HDR Image and Panorama Reconstruction
• Multi-domain Collaborative Feature Representation for Robust Visual Object Tracking