Parametrizing Product Shape Manifolds by Composite Networks

TL;DR

This paper introduces a neural network architecture that efficiently parametrizes shape manifolds with a product structure, reducing computational costs and accurately approximating complex shape spaces.

Contribution

The paper proposes a novel neural network framework that leverages the product structure of shape manifolds to improve approximation efficiency and accuracy.

Findings

Effective approximation of shape manifolds with low-dimensional factors

Successful application to triangular surface shape spaces

Demonstrated improvements on synthetic and real data

Abstract

Parametrizations of data manifolds in shape spaces can be computed using the rich toolbox of Riemannian geometry. This, however, often comes with high computational costs, which raises the question if one can learn an efficient neural network approximation. We show that this is indeed possible for shape spaces with a special product structure, namely those smoothly approximable by a direct sum of low-dimensional manifolds. Our proposed architecture leverages this structure by separately learning approximations for the low-dimensional factors and a subsequent combination. After developing the approach as a general framework, we apply it to a shape space of triangular surfaces. Here, typical examples of data manifolds are given through datasets of articulated models and can be factorized, for example, by a Sparse Principal Geodesic Analysis (SPGA). We demonstrate the effectiveness of our proposed approach with experiments on synthetic data as well as manifolds extracted from data via SPGA.