Conference item icon

Conference item

NeuralDiff: Segmenting 3D objects that move in egocentric videos

Abstract:

Given a raw video sequence taken from a freely-moving camera, we study the problem of decomposing the observed 3D scene into a static background and a dynamic foreground containing the objects that move within the scene. This task is reminiscent of the classic background subtraction problem, but is significantly harder because all parts of the scene, static and dynamic, generate a large apparent motion due to the camera large viewpoint change and parallax. In particular, we consider egocentri...

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

Actions


Access Document


Files:
Publisher copy:
10.1109/3dv53792.2021.00099

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Oxford college:
New College
Role:
Author
ORCID:
0000-0003-1374-2858
Publisher:
IEEE Publisher's website
Host title:
2021 International Conference on 3D Vision (3DV)
Pages:
910-919
Publication date:
2022-01-06
Acceptance date:
2021-10-01
Event title:
9th International Conference on 3D Vision (3DV)
Event location:
Virtual Event
Event website:
https://3dv2021.surrey.ac.uk/
Event start date:
2021-12-01
Event end date:
2021-12-03
DOI:
EISSN:
2475-7888
ISSN:
2378-3826
EISBN:
978-1-6654-2688-6
ISBN:
978-1-6654-2689-3
Language:
English
Keywords:
Pubs id:
1233319
Local pid:
pubs:1233319
Deposit date:
2022-01-26

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