Image Morphing in Deep Feature Spaces: Theory and Applications

TL;DR

This paper introduces a novel image morphing method leveraging deep feature spaces with a new variational discretization, demonstrating improved results over traditional intensity-based approaches.

Contribution

It develops a structure-sensitive, anisotropic flow regularization within a deep feature space framework and proves the existence and convergence of discrete geodesic paths.

Findings

Deep feature-based morphing outperforms intensity-based methods

Discrete geodesic paths converge to continuous models

Numerical experiments validate the proposed approach

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, Trouv\'e, Younes and coworkers. 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.