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
Authors
Funding
Bibliographic Details
- 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
Item Description
- Language:
- English
- Keywords:
- Pubs id:
-
1233319
- Local pid:
- pubs:1233319
- Deposit date:
- 2022-01-26
Terms of use
- Copyright holder:
- IEEE
- Copyright date:
- 2021
- Rights statement:
- © 2021 IEEE
- Notes:
- This is the accepted manuscript version of the paper. The final version is available online from IEEE at https://doi.org/10.1109/3DV53792.2021.00099
Metrics
If you are the owner of this record, you can report an update to it here: Report update to this record