CageNet: A Meta-Framework for Learning on Wild Meshes

TL;DR

CageNet introduces a flexible meta-framework using caged geometry and barycentric coordinates to enable learning on complex, wild meshes with irregular features, improving performance in segmentation and skinning tasks.

Contribution

The paper presents a novel meta-framework that extends generic mesh learning methods to wild, complex meshes through caged geometry and barycentric coordinate mappings.

Findings

Achieved better segmentation performance on wild meshes.

Improved skinning weight learning accuracy.

Demonstrated versatility across multiple mesh-based tasks.

Abstract

Learning on triangle meshes has recently proven to be instrumental to a myriad of tasks, from shape classification, to segmentation, to deformation and animation, to mention just a few. While some of these applications are tackled through neural network architectures which are tailored to the application at hand, many others use generic frameworks for triangle meshes where the only customization required is the modification of the input features and the loss function. Our goal in this paper is to broaden the applicability of these generic frameworks to "wild", i.e. meshes in-the-wild which often have multiple components, non-manifold elements, disrupted connectivity, or a combination of these. We propose a configurable meta-framework based on the concept of caged geometry: Given a mesh, a cage is a single component manifold triangle mesh that envelopes it closely. Generalized barycentric coordinates map between functions on the cage, and functions on the mesh, allowing us to learn and test on a variety of data, in different applications. We demonstrate this concept by learning segmentation and skinning weights on difficult data, achieving better performance to state of the art techniques on wild meshes.