Publication: Learning Depth With Very Sparse Supervision
Learning Depth With Very Sparse Supervision
Date
Date
Date
Citations
Loquercio, A., Dosovitskiy, A., & Scaramuzza, D. (2020). Learning Depth With Very Sparse Supervision. IEEE Robotics and Automation Letters, 5(4), 5542–5549. https://doi.org/10.1109/lra.2020.3009067
Abstract
Abstract
Abstract
Motivated by the astonishing capabilities of natural intelligent agents and inspired by theories from psychology, this paper explores the idea that perception gets coupled to 3D properties of the world via interaction with the environment. Existing works for depth estimation require either massive amounts of annotated training data or some form of hard-coded geometrical constraint. This paper explores a new approach to learning depth perception requiring neither of those. Specifically, we propose a novel global-local network architect
Metrics
Downloads
Views
Additional indexing
Creators (Authors)
- Loquercio, Antonio
- Dosovitskiy, Alexey
- Scaramuzza, Davide
Volume
Volume
Volume
Number
Number
Number
Page range/Item number
Page range/Item number
Page range/Item number
Page end
Page end
Page end
Item Type
Item Type
Item Type
In collections
Dewey Decimal Classifikation
Dewey Decimal Classifikation
Dewey Decimal Classifikation
Scope
Scope
Scope
Language
Language
Language
Publication date
Publication date
Publication date
Date available
Date available
Date available
ISSN or e-ISSN
ISSN or e-ISSN
ISSN or e-ISSN
OA Status
OA Status
OA Status
Publisher DOI
Other Identification Number
Other Identification Number
Other Identification Number
Metrics
Downloads
Views
Citations
Loquercio, A., Dosovitskiy, A., & Scaramuzza, D. (2020). Learning Depth With Very Sparse Supervision. IEEE Robotics and Automation Letters, 5(4), 5542–5549. https://doi.org/10.1109/lra.2020.3009067
