Single Image Super-Resolution with Dilated Convolution based Multi-Scale Information Learning Inception Module

22 Jul 2017 Wuzhen Shi Feng Jiang Debin Zhao

Traditional works have shown that patches in a natural image tend to redundantly recur many times inside the image, both within the same scale, as well as across different scales. Make full use of these multi-scale information can improve the image restoration performance... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Image Super-Resolution Set14 - 4x upscaling MSSRNet PSNR 27.83 # 36
SSIM 0.7631 # 39
Image Super-Resolution Set5 - 4x upscaling MSSRNet PSNR 31.10 # 31
SSIM 0.8777 # 35

Methods used in the Paper