Second-Order Attention Network for Single Image Super-Resolution

CVPR 2019 Tao Dai Jianrui Cai Yongbing Zhang Shu-Tao Xia Lei Zhang

Recently, deep convolutional neural networks (CNNs) have been widely explored in single image super-resolution (SISR) and obtained remarkable performance. However, most of the existing CNN-based SISR methods mainly focus on wider or deeper architecture design, neglecting to explore the feature correlations of intermediate layers, hence hindering the representational power of CNNs... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK LEADERBOARD
Image Super-Resolution BSD100 - 4x upscaling SAN PSNR 27.86 # 3
SSIM 0.7457 # 6
Image Super-Resolution Manga109 - 4x upscaling SAN PSNR 31.66 # 4
SSIM 0.9222 # 1
Image Super-Resolution Set14 - 4x upscaling SAN PSNR 29.05 # 2
SSIM 0.7921 # 6
Image Super-Resolution Set5 - 4x upscaling SAN PSNR 32.70 # 5
SSIM 0.9013 # 6
Image Super-Resolution Urban100 - 4x upscaling SAN PSNR 27.23 # 3
SSIM 0.8169 # 2