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

Guojing Jin, Jing Chen, Jingyao Wang, Yongtian Wang

科研成果: 书/报告/会议事项章节会议稿件同行评审

3 引用 (Scopus)

摘要

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.

源语言英语
主期刊名26th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2019 - Proceedings
出版商Institute of Electrical and Electronics Engineers Inc.
996-997
页数2
ISBN(电子版)9781728113777
DOI
出版状态已出版 - 3月 2019
活动26th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2019 - Osaka, 日本
期限: 23 3月 201927 3月 2019

出版系列

姓名26th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2019 - Proceedings

会议

会议26th IEEE Conference on Virtual Reality and 3D User Interfaces, VR 2019
国家/地区日本
Osaka
时期23/03/1927/03/19

指纹

探究 'A neural motion deblurring approach to restore rich textures for visual SLAM' 的科研主题。它们共同构成独一无二的指纹。

引用此