Thesis
Improving deep image feature matching
- Abstract:
-
Image matching establishes pixel correspondences between two images. It is usually achieved in two steps, where the high-dimensional local image features are first extracted across images and correspondences are established based on features' similarities. Image matching can be categorized into two sub-domains: geometric and semantic matching, where the former matches pixels describing the same 3D point while the latter finds pixels having the same semantic meaning. This thesis focuses on ...
Expand abstract
Actions
Access Document
- Files:
-
-
(Preview, Dissemination version, pdf, 17.4MB, Terms of use)
-
Authors
Contributors
+ Prisacariu, V
- Institution:
- University of Oxford
- Division:
- MPLS
- Department:
- Engineering Science
- Role:
- Supervisor
+ Vedaldi, A
- Institution:
- University of Oxford
- Division:
- MPLS
- Department:
- Engineering Science
- Role:
- Supervisor
+ Fallon, M
- Institution:
- University of Oxford
- Division:
- MPLS
- Department:
- Engineering Science
- Role:
- Examiner
- ORCID:
- 0000-0003-2940-0879
+ Arandjelović, R
- Institution:
- Google DeepMind
- Role:
- Examiner
- DOI:
- Type of award:
- DPhil
- Level of award:
- Doctoral
- Awarding institution:
- University of Oxford
- Language:
-
English
- Keywords:
- Subjects:
- Deposit date:
-
2025-06-23
- ARK identifier:
Terms of use
- Copyright holder:
- Xinghui Li
- Copyright date:
- 2025
If you are the owner of this record, you can report an update to it here: Report update to this record