Thesis
Deep representation learning for dynamic point cloud sequences
- Abstract:
-
Real-world environments are inherently dynamic, yet most point cloud processing methods assume static scenes. This fundamental limitation restricts the deployment of 3D perception systems in applications requiring temporal understanding, from autonomous navigation to human-robot interaction. This thesis presents three techniques for dynamic point cloud processing, each operating at a distinct level of representation—highlevel semantic understanding, intermediate-level motion analysis, and low...
Expand abstract
Actions
Access Document
- Files:
-
-
(Preview, Dissemination version, pdf, 9.0MB, Terms of use)
-
Authors
Contributors
+ Markham, A
- Institution:
- University of Oxford
- Division:
- MPLS
- Department:
- Computer Science
- Oxford college:
- Kellogg College
- Role:
- Supervisor
+ Trigoni, N
- Institution:
- University of Oxford
- Division:
- MPLS
- Department:
- Computer Science
- Oxford college:
- Kellogg College
- Role:
- Supervisor
+ University of Oxford
More from this funder
- Funder identifier:
- https://ror.org/052gg0110
- Programme:
- Lighthouse Graduate Scholarship
- DOI:
- Type of award:
- DPhil
- Level of award:
- Doctoral
- Awarding institution:
- University of Oxford
- Language:
-
English
- Deposit date:
-
2026-07-07
- ARK identifier:
Terms of use
- Copyright holder:
- Jiaxing Zhong
- Copyright date:
- 2026
If you are the owner of this record, you can report an update to it here: Report update to this record