Conference item icon

Conference item

Thinking outside the box: Generation of unconstrained 3D room layouts

Abstract:

We propose a method for room layout estimation that does not rely on the typical box approximation or Manhattan world assumption. Instead, we reformulate the geometry inference problem as an instance detection task, which we solve by directly regressing 3D planes using an R-CNN. We then use a variant of probabilistic clustering to combine the 3D planes regressed at each frame in a video sequence, with their respective camera poses, into a single global 3D room layout estimate. Finally, we sho...

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

Actions


Access Document


Files:
  • (Accepted manuscript, pdf, 5.2MB)
Publisher copy:
10.1007/978-3-030-20887-5_27

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Engineering Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS Division
Department:
Engineering Science
Role:
Author
ORCID:
0000-0003-4216-8074
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Oxford college:
St Anne's College
Role:
Author
European Commission Project More from this funder
Publisher:
Springer Publisher's website
Volume:
11361
Pages:
432-448
Series:
Lecture Notes in Computer Science
Host title:
Computer Vision – ACCV 2018
Publication date:
2019-05-28
Acceptance date:
2018-09-21
DOI:
Source identifiers:
921485
ISBN:
9783030208868
Keywords:
Pubs id:
pubs:921485
UUID:
uuid:3b72f44d-0cdd-4d3e-ae07-6cc897d19acf
Local pid:
pubs:921485
Deposit date:
2019-07-17

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