A Flexible Deep CNN Framework for Image Restoration

Zhi Jin, Muhammad Zafar Iqbal, Dmytro Bobkov, Wenbin Zou, Xia Li, Eckehard Steinbach

Research output: Contribution to journalArticlepeer-review

70 Scopus citations


Image restoration is a long-standing problem in image processing and low-level computer vision. Recently, discriminative convolutional neural network (CNN)-based approaches have attracted considerable attention due to their superior performance. However, most of these frameworks are designed for one specific image restoration task; hence, they seldom show high performance on other image restoration tasks. To address this issue, we propose a flexible deep CNN framework that exploits the frequency characteristics of different types of artifacts. Hence, the same approach can be employed for a variety of image restoration tasks by adjusting the architecture. For reducing the artifacts with similar frequency characteristics, a quality enhancement network that adopts residual and recursive learning is proposed. Residual learning is utilized to speed up the training process and boost the performance; recursive learning is adopted to significantly reduce the number of training parameters as well as boost the performance. Moreover, lateral connections transmit the extracted features between different frequency streams via multiple paths. One aggregation network combines the outputs of these streams to further enhance the restored images. We demonstrate the capabilities of the proposed framework with three representative applications: image compression artifacts reduction (CAR), image denoising, and single image super-resolution (SISR). Extensive experiments confirm that the proposed framework outperforms the state-of-the-art approaches on benchmark datasets for these applications.

Original languageEnglish
Article number8820082
Pages (from-to)1055-1068
Number of pages14
JournalIEEE Transactions on Multimedia
Issue number4
StatePublished - 1 Apr 2020


  • Image restoration
  • flexible CNN framework
  • image decomposition
  • recursive learning
  • residual learning


Dive into the research topics of 'A Flexible Deep CNN Framework for Image Restoration'. Together they form a unique fingerprint.

Cite this