Image Super-Resolution Using Deep Convolutional Networks

Code

• github.com/TanakitInt/SRCNN-anime
  tf★ 27
• github.com/george-gca/sr-pytorch-lightning
  pytorch★ 21
• github.com/arjunarao619/SRCNN_Pytorch
  pytorch★ 5
• github.com/Weifeng73/Zero-Shot-Super-resolution
  none★ 1
• github.com/amzamzamzamz/nagadomi-waifu2x
  torch★ 0
• github.com/mayank-17/Project-Image-Restoration-using-SRCNN
  none★ 0
• github.com/HighVoltageRocknRoll/sr
  tf★ 0
• github.com/aba450/Super-Resolution
  pytorch★ 0
• github.com/teakkkz/imageSR
  tf★ 0
• github.com/dokyeongK/Single-Image-Super-Resolution-Reimplemenation
  pytorch★ 0

Abstract

We propose a deep learning method for single image super-resolution (SR). Our method directly learns an end-to-end mapping between the low/high-resolution images. The mapping is represented as a deep convolutional neural network (CNN) that takes the low-resolution image as the input and outputs the high-resolution one. We further show that traditional sparse-coding-based SR methods can also be viewed as a deep convolutional network. But unlike traditional methods that handle each component separately, our method jointly optimizes all layers. Our deep CNN has a lightweight structure, yet demonstrates state-of-the-art restoration quality, and achieves fast speed for practical on-line usage. We explore different network structures and parameter settings to achieve trade-offs between performance and speed. Moreover, we extend our network to cope with three color channels simultaneously, and show better overall reconstruction quality.

Tasks

Benchmark Results

Reproductions