Multi-stage feature-fusion dense network for motion deblurring

Cai Guo, Qian Wang, Hong Ning Dai*, Ping Li

*Corresponding author for this work

Research output: Contribution to journalJournal articlepeer-review

2 Citations (Scopus)


Although convolutional neural networks (CNNs) have recently shown considerable progress in motion deblurring, most existing methods that adopt multi-scale input schemes are still challenging in accurately restoring the heavily-blurred regions in blurry images. Several recent methods aim to further improve the deblurring effect using larger and more complex models, but these methods inevitably result in huge computing costs. To address the performance-complexity trade-off, we propose a multi-stage feature-fusion dense network (MFFDNet) for motion deblurring. Each sub-network of our MFFDNet has the similar structure and the same scale of input. Meanwhile, we propose a feature-fusion dense connection structure to reuse the extracted features, thereby improving the deblurring effect. Moreover, instead of using the multi-scale loss function, we only calculate the loss function at the output of the last stage since the input scale of our sub-network is invariant. Experimental results show that MFFDNet maintains a relatively small computing cost while outperforming state-of-the-art motion-deblurring methods. The source code is publicly available at:

Original languageEnglish
Article number103717
JournalJournal of Visual Communication and Image Representation
Publication statusPublished - Feb 2023

Scopus Subject Areas

  • Signal Processing
  • Electrical and Electronic Engineering
  • Computer Vision and Pattern Recognition
  • Media Technology

User-Defined Keywords

  • Channel-based multi-layer perceptrons
  • Feature-fusion dense connections
  • Motion deblurring
  • Multi-stage network


Dive into the research topics of 'Multi-stage feature-fusion dense network for motion deblurring'. Together they form a unique fingerprint.

Cite this