A neural motion deblurring approach to restore rich textures for visual SLAM

Guojing Jin, Jing Chen, Jingyao Wang, Yongtian Wang

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

3 Citations (Scopus)

Abstract

In this paper, we present a sequential video deblurring method based on a spatio-temporal recurrent network for visual SLAM. The method can be applied to any SLAM systems to make sure continuous localization even with blurred images. The quality of the deblurring method is evaluated on real-world problems: Feature points extraction and SLAM, which prove the method can significantly improve the performance of tracking accuracy especially in some severe cases containing strong camera shake or fast motion.

Original languageEnglish
Title of host publication26th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2019 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages996-997
Number of pages2
ISBN (Electronic)9781728113777
DOIs
Publication statusPublished - Mar 2019
Event26th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2019 - Osaka, Japan
Duration: 23 Mar 201927 Mar 2019

Publication series

Name26th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2019 - Proceedings

Conference

Conference26th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2019
Country/TerritoryJapan
CityOsaka
Period23/03/1927/03/19

Keywords

  • Deblur
  • Motion blur
  • SLAM

Fingerprint

Dive into the research topics of 'A neural motion deblurring approach to restore rich textures for visual SLAM'. Together they form a unique fingerprint.

Cite this