Deep neural networks on diffeomorphism groups for optimal shape reparametrization

DOI10.1007/S10543-023-00989-5zbMATH Open1526.65027arXiv2207.11141WikidataQ125560861 ScholiaQ125560861MaRDI QIDQ6093564FDOQ6093564

Authors: Elena Celledoni, Helge Glöckner, Jørgen N. Riseth, Alexander Schmeding 

Publication date: 9 October 2023

Published in: BIT (Search for Journal in Brave)

Abstract: In shape analysis, one of the fundamental problems is to align curves or surfaces before computing a (geodesic) distance between these shapes. To find the optimal reparametrization realizing this alignment is a computationally demanding task which leads to an optimization problem on the diffeomorphism group. In this paper, we construct approximations of orientation-preserving diffeomorphisms by composition of elementary diffeomorphisms to solve the approximation problem. We propose a practical algorithm implemented in PyTorch which is applicable both to unparametrized curves and surfaces. We derive universal approximation results and obtain bounds for the Lipschitz constant of the obtained compositions of diffeomorphisms.

Full work available at URL: https://arxiv.org/abs/2207.11141

Recommendations

• Riemannian geometry on shapes and diffeomorphisms
• Riemannian optimization for registration of curves in elastic shape analysis
• Deep learning approximation of diffeomorphisms via linear-control systems
• Diffeomorphic learning
• A sub-Riemannian modular framework for diffeomorphism-based analysis of shape ensembles

zbMATH Keywords

deep learningshape analysisdiffeomorphism groupoptimal reparametrization

Mathematics Subject Classification ID

Numerical optimization and variational techniques (65K10) Groups of diffeomorphisms and homeomorphisms as manifolds (58D05) Manifolds of mappings (46T10)

Cites Work

• Title not available (Why is that?)
• Controllability on the group of diffeomorphisms
• Title not available (Why is that?)
• The inverse function theorem of Nash and Moser
• Towards a Lie theory of locally convex groups
• Approximation by superpositions of a sigmoidal function
• Title not available (Why is that?)
• When unit groups of continuous inverse algebras are regular Lie groups
• The blossoming of Schröder's fourth problem
• Infinite dimensional Lie transformation groups
• Cubic convolution interpolation for digital image processing
• Constructing reparameterization invariant metrics on spaces of plane curves
• Structure-preserving deep learning
• Density estimation by dual ascent of the log-likelihood
• Stable architectures for deep neural networks
• A proposal on machine learning via dynamical systems
• Title not available (Why is that?)
• Diffeomorphism groups of compact convex sets
• Shape analysis of surfaces using general elastic metrics
• Deep learning as optimal control problems: models and numerical methods
• Shape analysis on Lie groups and homogeneous spaces
• Shape analysis on Lie groups with applications in computer animation
• Closed surfaces with different shapes that are indistinguishable by the SRNF.
• Regularity of Lie groups
• Control on the manifolds of mappings with a view to the deep learning

Cited In (2)

• Designing stable neural networks using convex analysis and ODEs
• Constrained dynamics, stochastic numerical methods and the modeling of complex systems. Abstracts from the workshop held May 26--31, 2024

This page was built for publication: Deep neural networks on diffeomorphism groups for optimal shape reparametrization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6093564)