Revitalizing Convolutional Network for Image Restoration

Yuning Cui, Wenqi Ren, Xiaochun Cao, Alois Knoll

Research output: Contribution to journalArticlepeer-review


Image restoration aims to reconstruct a high-quality image from its corrupted version, playing essential roles in many scenarios. Recent years have witnessed a paradigm shift in image restoration from convolutional neural networks (CNNs) to Transformerbased models due to their powerful ability to model long-range pixel interactions. In this paper, we explore the potential of CNNs for image restoration and show that the proposed simple convolutional network architecture, termed ConvIR, can perform on par with or better than the Transformer counterparts. By re-examing the characteristics of advanced image restoration algorithms, we discover several key factors leading to the performance improvement of restoration models. This motivates us to develop a novel network for image restoration based on cheap convolution operators. Comprehensive experiments demonstrate that our ConvIR delivers state-ofthe- art performance with low computation complexity among 20 benchmark datasets on five representative image restoration tasks, including image dehazing, image motion/defocus deblurring, image deraining, and image desnowing.

Original languageEnglish
Pages (from-to)1-16
Number of pages16
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
StateAccepted/In press - 2024


  • Computational modeling
  • Computer architecture
  • Convolution
  • Convolutional neural networks
  • Frequency modulation
  • frequency modulation
  • image restoration
  • Image restoration
  • representation learning
  • Task analysis
  • Transformers


Dive into the research topics of 'Revitalizing Convolutional Network for Image Restoration'. Together they form a unique fingerprint.

Cite this