Enhanced Deep Residual Networks for Single Image Super-Resolution

10 Jul 2017Bee LimSanghyun SonHeewon KimSeungjun NahKyoung Mu Lee

Recent research on super-resolution has progressed with the development of deep convolutional neural networks (DCNN). In particular, residual learning techniques exhibit improved performance... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Image Super-Resolution BSD100 - 4x upscaling EDSR PSNR 27.71 # 11
SSIM 0.7420 # 13
Image Super-Resolution Manga109 - 4x upscaling EDSR PSNR 31.02 # 10
SSIM 0.9148 # 10
Image Super-Resolution Set14 - 4x upscaling EDSR PSNR 28.80 # 13
SSIM 0.7876 # 14
Image Super-Resolution Set5 - 4x upscaling EDSR PSNR 32.46 # 11
SSIM 0.8968 # 14
Image Super-Resolution Urban100 - 4x upscaling EDSR PSNR 26.64 # 12
SSIM 0.8033 # 9

Results from Other Papers


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK SOURCE PAPER COMPARE
Image Super-Resolution FFHQ 1024 x 1024 - 4x upscaling EDSR FID 15.54 # 2
MS-SSIM 0.933 # 4
PSNR 28.34 # 3
SSIM 0.827 # 3
Image Super-Resolution FFHQ 256 x 256 - 4x upscaling EDSR FID 129.14 # 3
MS-SSIM 0.901 # 3
PSNR 22.47 # 4
SSIM 0.706 # 3