Conference item
Keep geometry in context: using contextual priors for very-large-scale 3D dense reconstructions
- Abstract:
-
This paper is about the efficient generation of dense models of very large-scale environments from depth data and in particular, stereo-camera-based depth data. Better maps make for better understanding; better understanding leads to better robots, but this comes at a cost: the computational and memory requirements of large dense models can be prohibitive.
We provide the theory and the system needed to create verylarge- scale dense reconstructions. To this end, we leverage three sou...
Expand abstract
- Publication status:
- Published
- Peer review status:
- Peer reviewed
Actions
Authors
Funding
Bibliographic Details
- Publisher:
- Robotics: Science and Systems Publisher's website
- Journal:
- RSS 2016 Workshop: Geometry and Beyond - Representations, Physics, and Scene Understanding for Robotics, Sunday, June 19 2016, University of Michigan Journal website
- Host title:
- RSS 2016 Workshop: Geometry and Beyond - Representations, Physics, and Scene Understanding for Robotics, Sunday, June 19 2016, University of Michigan
- Publication date:
- 2016-01-01
- Acceptance date:
- 2016-05-23
- Source identifiers:
-
820373
Item Description
- Pubs id:
-
pubs:820373
- UUID:
-
uuid:b5f4e591-0078-49fc-a26a-ce4459473fe0
- Local pid:
- pubs:820373
- Deposit date:
- 2018-01-18
Terms of use
- Copyright date:
- 2016
If you are the owner of this record, you can report an update to it here: Report update to this record