Abstract
This paper combines image metamorphosis with deep features. To this end, images are considered as maps into a high-dimensional feature space and a structure-sensitive, anisotropic flow regularization is incorporated in the metamorphosis model proposed by Miller and Younes (Int J Comput Vis 41(1):61–84, 2001) and Trouvé and Younes (Found Comput Math 5(2):173–198, 2005). For this model, a variational time discretization of the Riemannian path energy is presented and the existence of discrete geodesic paths minimizing this energy is demonstrated. Furthermore, convergence of discrete geodesic paths to geodesic paths in the time continuous model is investigated. The spatial discretization is based on a finite difference approximation in image space and a stable spline approximation in deformation space; the fully discrete model is optimized using the iPALM algorithm. Numerical experiments indicate that the incorporation of semantic deep features is superior to intensity-based approaches.
Original language | English |
---|---|
Pages (from-to) | 309-327 |
Number of pages | 19 |
Journal | Journal of Mathematical Imaging and Vision |
Volume | 63 |
Issue number | 2 |
Early online date | 19 Jul 2020 |
DOIs | |
Publication status | Published - Feb 2021 |
Keywords
- Convolutional neural networks
- Image morphing
- Metamorphosis model
- Mosco convergence
- Variational time discretization
ASJC Scopus subject areas
- Condensed Matter Physics
- Applied Mathematics
- Geometry and Topology
- Computer Vision and Pattern Recognition
- Statistics and Probability
- Modelling and Simulation