Abstract:Continuous image morphing is a classical task in image processing. The metamorphosis model proposed by Trouvé, Younes and coworkers [39,53] casts this problem in the frame of Riemannian geometry and geodesic paths between images. The associated metric in the space of images incorporates dissipation caused by a viscous flow transporting image intensities and its variations along motion paths. In many applications, images are maps from the image domain into a manifold (e.g. in DTI imaging the manifold of symmetr… Show more
“…is identical to the corresponding reasoning in [13]. At this point, we also observe that the velocity field w K with…”
Section: Convergence Of Discrete Geodesic Pathssupporting
confidence: 82%
“…is uniformly bounded in L 2 ((0, 1), V) and thus converges weakly in L 2 ((0, 1), V) to some limit velocity field v. This fact is again proved following the corresponding reasoning as in [13].…”
Section: Convergence Of Discrete Geodesic Pathsmentioning
confidence: 59%
“…holds true, which follows from Korn's inequality and the Poincaré inequality. Thus, the lemma follows by combining (11), (12), (13) and (14).…”
Section: Lemma 1 Let (W1)-(w2) and (A1) Be Satisfied Then There Eximentioning
confidence: 93%
“…In [13,Section 3], the equivalence of this energy functional and (3) in the isotropic case has been shown. Let ψ as above denote the Lagrangian flow map induced by the Eulerian motion field withψ…”
Section: Metamorphosis Model In Deep Feature Spacementioning
confidence: 98%
“…(ii) Recovery sequence. Before constructing the recovery sequence, we note that the infimum in (6) is actually attained with an associated pair (v, z) ∈ C( f ), which follows from [13,Proposition 5.3] together with Remark 1.…”
Section: Convergence Of Discrete Geodesic Pathsmentioning
This paper combines image metamorphosis with deep features. To this end, images are considered as maps into a highdimensional feature space and a structure-sensitive, anisotropic flow regularization is incorporated in the metamorphosis model proposed by Miller and Younes (
“…is identical to the corresponding reasoning in [13]. At this point, we also observe that the velocity field w K with…”
Section: Convergence Of Discrete Geodesic Pathssupporting
confidence: 82%
“…is uniformly bounded in L 2 ((0, 1), V) and thus converges weakly in L 2 ((0, 1), V) to some limit velocity field v. This fact is again proved following the corresponding reasoning as in [13].…”
Section: Convergence Of Discrete Geodesic Pathsmentioning
confidence: 59%
“…holds true, which follows from Korn's inequality and the Poincaré inequality. Thus, the lemma follows by combining (11), (12), (13) and (14).…”
Section: Lemma 1 Let (W1)-(w2) and (A1) Be Satisfied Then There Eximentioning
confidence: 93%
“…In [13,Section 3], the equivalence of this energy functional and (3) in the isotropic case has been shown. Let ψ as above denote the Lagrangian flow map induced by the Eulerian motion field withψ…”
Section: Metamorphosis Model In Deep Feature Spacementioning
confidence: 98%
“…(ii) Recovery sequence. Before constructing the recovery sequence, we note that the infimum in (6) is actually attained with an associated pair (v, z) ∈ C( f ), which follows from [13,Proposition 5.3] together with Remark 1.…”
Section: Convergence Of Discrete Geodesic Pathsmentioning
This paper combines image metamorphosis with deep features. To this end, images are considered as maps into a highdimensional feature space and a structure-sensitive, anisotropic flow regularization is incorporated in the metamorphosis model proposed by Miller and Younes (
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.