Skip to main navigation Skip to search Skip to main content

Dense block u-net for dynamic scene deblurring

  • Yujie Wu
  • , Hong Zhang
  • , Yawei Li
  • , Yinan Mao
  • , Lei He
  • , Zhoufeng Liu
  • Beihang University
  • Luoyang Electro-optical Equipment Research Institute
  • Zhongyuan University of Technology

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Motion blur often arises in a single image because of the camera shake, the objects motion and the depth variation. The image deblurring is a challenging task due to its ill-posed nature. To remove these blurriness, the conventional energy optimization based methods always rely on the assumption such that the blur kernel is uniform across the entire image. With the development of the deep neural network, the learning based methods were proposed to tackle with the non-uniform blur cases. In this paper, we propose a U-Net network containing dense blocks for dynamic scene deblurring. By passing the kernel estimation, our model significantly reduces the inference time. The extensive experiments on both synthetic and real blurred images demonstrate that our method outperforms the state-of-The-Art blind deblurring algorithms.

Original languageEnglish
Title of host publicationICGSP 2020 - Proceedings of the 4th International Conference on Graphics and Signal Processing
PublisherAssociation for Computing Machinery
Pages46-50
Number of pages5
ISBN (Electronic)9781450377812
DOIs
StatePublished - 26 Jun 2020
Event4th International Conference on Graphics and Signal Processing, ICGSP 2020 - Nagoya, Virtual, Japan
Duration: 26 Jun 202028 Jun 2020

Publication series

NameACM International Conference Proceeding Series

Conference

Conference4th International Conference on Graphics and Signal Processing, ICGSP 2020
Country/TerritoryJapan
CityNagoya, Virtual
Period26/06/2028/06/20

Keywords

  • Blind deblurring
  • U-net
  • dense block
  • non-uniform

Fingerprint

Dive into the research topics of 'Dense block u-net for dynamic scene deblurring'. Together they form a unique fingerprint.

Cite this