Transferable Foundation Models for Geometric Tasks on Point Cloud Representations: Geometric Neural Operators
This work addresses the need for reusable foundation models for geometric tasks in machine learning and numerical methods, offering a tool for data processing pipelines and solvers.
The authors tackled the problem of learning robust geometric features from point clouds by introducing pretrained Geometric Neural Operators (GNPs), which provide estimates of metric, curvature, and shape-related features with robustness to noise and applicability to arbitrary shapes and topologies.
We introduce methods for obtaining pretrained Geometric Neural Operators (GNPs) that can serve as basal foundation models for use in obtaining geometric features. These can be used within data processing pipelines for machine learning tasks and numerical methods. We show how our GNPs can be trained to learn robust latent representations for the differential geometry of point-clouds to provide estimates of metric, curvature, and other shape-related features. We demonstrate how our pre-trained GNPs can be used (i) to estimate the geometric properties of surfaces of arbitrary shape and topologies with robustness in the presence of noise, (ii) to approximate solutions of geometric partial differential equations (PDEs) on manifolds, and (iii) to solve equations for shape deformations such as curvature driven flows. We release codes and weights for using GNPs in the package geo_neural_op. This allows for incorporating our pre-trained GNPs as components for reuse within existing and new data processing pipelines. The GNPs also can be used as part of numerical solvers involving geometry or as part of methods for performing inference and other geometric tasks.