Compression artifacts reduction by a deep convolutional network

  • Dong C
  • Deng Y
  • Loy C
 et al. 
  • 162


    Mendeley users who have this article in their library.
  • 61


    Citations of this article.


Lossy compression introduces complex compression artifacts, particularly the blocking artifacts, ringing effects and blurring. Existing algorithms either focus on removing blocking artifacts and produce blurred output, or restores sharpened images that are accompanied with ringing effects. Inspired by the deep convolutional networks (DCN) on super-resolution, we formulate a compact and efficient network for seamless attenuation of different compression artifacts. We also demonstrate that a deeper model can be effectively trained with the features learned in a shallow network. Following a similar "easy to hard" idea, we systematically investigate several practical transfer settings and show the effectiveness of transfer learning in low-level vision problems. Our method shows superior performance than the state-of-the-arts both on the benchmark datasets and the real-world use case (i.e. Twitter). In addition, we show that our method can be applied as pre-processing to facilitate other low-level vision routines when they take compressed images as input.

Get free article suggestions today

Mendeley saves you time finding and organizing research

Sign up here
Already have an account ?Sign in

Find this document


  • Chao Dong

  • Yubin Deng

  • Chen Change Loy

  • Xiaoou Tang

Cite this document

Choose a citation style from the tabs below

Save time finding and organizing research with Mendeley

Sign up for free