articleIEEE Transactions on Pattern Analysis and Machine IntelligenceJun 25, 2024GREEN OA

Revitalizing Convolutional Network for Image Restoration

YCYuning CuiWRWenqi RenXCXiaochun CaoAKAlois Knoll

Technical University of Munich · Sun Yat-sen University

PubMed
Indexed incrossrefpubmed

Abstract

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 Transformer-based 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…

Citation impact

169
total citations
FWCI
38.08
Percentile
100%
References
112
Citations per year

Authors

4

Topics & keywords

Topics
Keywords
  • Image restoration
  • Deblurring
  • Computer science
  • Artificial intelligence
  • Convolutional neural network
  • Benchmark (surveying)
  • Image (mathematics)
  • Convolution (computer science)
UN Sustainable Development Goals
  • Sustainable cities and communities
No related works found for this paper.

Funding