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
Actions
Access Document
- Files:
-
-
(Accepted manuscript, pdf, 3.4MB)
-
- Publisher copy:
- 10.1007/978-3-030-01249-6_43
Authors
Funding
Continental Corporation
More from this funder
Bibliographic Details
- Publisher:
- Springer Publisher's website
- Journal:
- European Conference on Computer Vision (ECCV 2018) Journal website
- Host title:
- European Conference on Computer Vision (ECCV 2018)
- Publication date:
- 2018-10-06
- Acceptance date:
- 2018-07-03
- DOI:
- ISSN:
-
0302-9743 and 1611-3349
- Source identifiers:
-
940497
- ISBN:
- 9783030012489
Item Description
- Pubs id:
-
pubs:940497
- UUID:
-
uuid:45401dc3-44cb-4e74-a589-16937f5c3450
- Local pid:
- pubs:940497
- Deposit date:
- 2018-11-16
Terms of use
- Copyright holder:
- Springer Nature Switzerland AG
- Copyright date:
- 2018
- Notes:
- © Springer Nature Switzerland AG 2018. This is the accepted manuscript version of the article. The final version is available online from Springer at: https://doi.org/10.1007/978-3-030-01249-6_43
If you are the owner of this record, you can report an update to it here: Report update to this record