Abstract
Groupwise non-rigid image alignment is a difficult non-linear optimisation problem, involving many parameters and often large datasets. Previous methods have explored various metrics and optimisation strategies. Good results have been
previously achieved with simple metrics, but requiring complex optimisation, often with many unintuitive parameters that require careful tuning for each dataset. In this paper we restructure the problem to use a simpler, iterative optimisation algorithm, with very few free parameters. We demonstrate how to incorporate a stiffness constraint and how to tune the few remaining parameters. Results show that the method reliably aligns various datasets and demonstrates efficiency in terms performance and reduction of the computations.
previously achieved with simple metrics, but requiring complex optimisation, often with many unintuitive parameters that require careful tuning for each dataset. In this paper we restructure the problem to use a simpler, iterative optimisation algorithm, with very few free parameters. We demonstrate how to incorporate a stiffness constraint and how to tune the few remaining parameters. Results show that the method reliably aligns various datasets and demonstrates efficiency in terms performance and reduction of the computations.
Original language | English |
---|---|
Pages | 245-252 |
Number of pages | 8 |
Publication status | Published - 18 Jul 2018 |
Event | International Conference on Computer Graphics, Visualization, Computer Vision and Image Processing (CGVCVIP) 2018 - Madrid, Spain Duration: 18 Jul 2018 → 20 Jul 2018 |
Conference
Conference | International Conference on Computer Graphics, Visualization, Computer Vision and Image Processing (CGVCVIP) 2018 |
---|---|
Abbreviated title | CGVCVIP |
Country/Territory | Spain |
City | Madrid |
Period | 18 Jul 2018 → 20 Jul 2018 |
Keywords
- Non-Rigid Image Alignment
- Groupwise Registration