Shape Space Spectra
Yue Chang, Otman Benchekroun, Maurizio M. Chiaramonte, Peter Yichen Chen, Eitan Grinspun

TL;DR
This paper introduces a novel eigenanalysis method for continuously parameterized shape families, enabling shape space modeling, optimization, and reduced-order modeling across diverse shapes using neural fields.
Contribution
It presents the first eigenanalysis approach for shape families that is agnostic to shape representation and supports differentiable optimization over shape space.
Findings
Enables vibration mode analysis across shape space including unseen shapes
Facilitates shape optimization using eigenfunction gradients
Improves reduced-order modeling for elastodynamics
Abstract
Eigenanalysis of differential operators, such as the Laplace operator or elastic energy Hessian, is typically restricted to a single shape and its discretization, limiting reduced order modeling (ROM). We introduce the first eigenanalysis method for continuously parameterized shape families. Given a parametric shape, our method constructs spatial neural fields that represent eigenfunctions across the entire shape space. It is agnostic to the specific shape representation, requiring only an inside/outside indicator function that depends on shape parameters. Eigenfunctions are computed by minimizing a variational principle over nested spaces with orthogonality constraints. Since eigenvalues may swap dominance at points of multiplicity, we jointly train multiple eigenfunctions while dynamically reordering them based on their eigenvalues at each step. Through causal gradient filtering, this…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsImage Processing and 3D Reconstruction · Neural Networks and Applications · Topological and Geometric Data Analysis
