MAMNet: Multi-path Adaptive Modulation Network for Image Super-Resolution

29 Nov 2018Jun-Hyuk KimJun-Ho ChoiManri CheonJong-Seok Lee

In recent years, single image super-resolution (SR) methods based on deep convolutional neural networks (CNNs) have made significant progress. However, due to the non-adaptive nature of the convolution operation, they cannot adapt to various characteristics of images, which limits their representational capability and, consequently, results in unnecessarily large model sizes... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Image Super-Resolution BSD100 - 4x upscaling SRRAM PSNR 27.56 # 16
SSIM 0.7350 # 21
Image Super-Resolution Set14 - 4x upscaling SRRAM PSNR 28.54 # 18
SSIM 0.7800 # 24
Image Super-Resolution Set5 - 4x upscaling SRRAM PSNR 32.13 # 15
SSIM 0.8932 # 19
Image Super-Resolution Urban100 - 4x upscaling SRRAM PSNR 26.05 # 18
SSIM 0.7834 # 17

Methods used in the Paper