Deeply-Recursive Convolutional Network for Image Super-Resolution

CVPR 2016 Jiwon KimJung Kwon LeeKyoung Mu Lee

We propose an image super-resolution method (SR) using a deeply-recursive convolutional network (DRCN). Our network has a very deep recursive layer (up to 16 recursions)... (read more)

PDF Abstract

Evaluation results from the paper


Task Dataset Model Metric name Metric value Global rank Compare
Image Super-Resolution BSD100 - 4x upscaling DRCN PSNR 27.21 # 23
Image Super-Resolution BSD100 - 4x upscaling DRCN SSIM 0.7493 # 3
Image Super-Resolution BSD100 - 4x upscaling DRCN MOS 2.12 # 3
Image Super-Resolution Set14 - 4x upscaling DRCN PSNR 28.02 # 25
Image Super-Resolution Set14 - 4x upscaling DRCN SSIM 0.8074 # 3
Image Super-Resolution Set14 - 4x upscaling DRCN MOS 2.84 # 3
Image Super-Resolution Set5 - 4x upscaling DRCN PSNR 31.52 # 18
Image Super-Resolution Set5 - 4x upscaling DRCN SSIM 0.8938 # 14
Image Super-Resolution Set5 - 4x upscaling DRCN MOS 3.26 # 3