Conference item icon

Conference item

Moving SLAM: fully unsupervised deep learning in non-rigid scenes

Abstract:

We propose a new deep learning framework to decompose monocular videos into 3D geometry (camera pose and depth), moving objects, and their motions, with no supervision. We build upon the idea of view synthesis, which uses classical camera geometry to re-render a source image from a different point-of-view to obtain supervisory signals, specified by a predicted relative 6-degree-of-freedom pose and depth map. However, the typical view synthesis equations rely on a strong assumption: that objec...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Files:
Publisher copy:
10.1109/iros51168.2021.9636075

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Oxford college:
New College
Role:
Author
ORCID:
0000-0003-1374-2858
Publisher:
IEEE
Host title:
Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2021)
Pages:
4611-4617
Publication date:
2021-09-27
Event title:
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2021)
Event location:
Prague, Czech Republic
Event website:
https://www.iros2021.org/
Event start date:
2021-09-27
Event end date:
2021-10-01
DOI:
EISSN:
2153-0866
ISSN:
2153-0858
EISBN:
978-1-6654-1714-3
ISBN:
978-1-6654-1715-0
Language:
English
Keywords:
Pubs id:
1233294
Local pid:
pubs:1233294
Deposit date:
2022-01-25

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP