Conference item icon

Conference item

Supervising the new with the old: Learning SFM from SFM

Abstract:

Recent work has demonstrated that it is possible to learn deep neural networks for monocular depth and ego-motion estimation from unlabelled video sequences, an interesting theoretical development with numerous advantages in applications. In this paper, we propose a number of improvements to these approaches. First, since such self-supervised approaches are based on the brightness constancy assumption, which is valid only for a subset of pixels, we propose a probabilistic learning formulation...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed
Version:
Accepted manuscript

Actions


Access Document


Files:
Publisher copy:
10.1007/978-3-030-01249-6_43

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Engineering Science
Oxford college:
New College; New College; New College; New College
Role:
Author
Continental Corporation More from this funder
Publisher:
Springer Publisher's website
Publication date:
2018-10-06
Acceptance date:
2018-07-03
DOI:
ISSN:
0302-9743 and 1611-3349
Pubs id:
pubs:940497
URN:
uri:45401dc3-44cb-4e74-a589-16937f5c3450
UUID:
uuid:45401dc3-44cb-4e74-a589-16937f5c3450
Local pid:
pubs:940497
ISBN:
9783030012489

Terms of use


Metrics


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