Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connections

29 Jun 2016 Xiao-Jiao Mao Chunhua Shen Yu-Bin Yang

Image restoration, including image denoising, super resolution, inpainting, and so on, is a well-studied problem in computer vision and image processing, as well as a test bed for low-level image modeling algorithms. In this work, we propose a very deep fully convolutional auto-encoder network for image restoration, which is a encoding-decoding framework with symmetric convolutional-deconvolutional layers... (read more)

PDF Abstract

Datasets


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Image Super-Resolution BSD100 - 2x upscaling RED30 PSNR 31.99 # 11
SSIM 0.8974 # 5
Image Super-Resolution BSD100 - 3x upscaling RED30 PSNR 28.93 # 6
SSIM 0.7994 # 4
Image Super-Resolution BSD100 - 4x upscaling RED30 PSNR 27.4 # 24
SSIM 0.729 # 30
Grayscale Image Denoising BSD200 sigma10 RED30 PSNR 33.63 # 2
SSIM 0.9319 # 1
Grayscale Image Denoising BSD200 sigma30 RED30 PSNR 27.95 # 3
SSIM 0.8019 # 1
Grayscale Image Denoising BSD200 sigma50 RED30 PSNR 25.75 # 3
SSIM 0.7167 # 1
Grayscale Image Denoising BSD200 sigma70 RED30 PSNR 24.37 # 3
SSIM 0.6551 # 1
JPEG Artifact Correction Live1 (Quality 10 Grayscale) RED30 PSNR 29.35 # 8
JPEG Artifact Correction LIVE1 (Quality 20 Grayscale) RED30 PSNR 31.73 # 6
Image Super-Resolution Set14 - 2x upscaling RED30 PSNR 32.94 # 16
SSIM 0.9144 # 7
Image Super-Resolution Set14 - 3x upscaling RED30 PSNR 29.61 # 8
SSIM 0.8341 # 3
Image Super-Resolution Set14 - 4x upscaling RED30 PSNR 27.86 # 35
SSIM 0.7718 # 34
Image Super-Resolution Set5 - 2x upscaling RED30 PSNR 37.66 # 14
SSIM 0.9599 # 8
Image Super-Resolution Set5 - 3x upscaling RED30 PSNR 33.82 # 11
SSIM 0.923 # 6
Image Super-Resolution Set5 - 4x upscaling RED30 PSNR 31.51 # 27
SSIM 0.8869 # 30

Methods used in the Paper


METHOD TYPE
Convolution
Convolutions