Frame Averaging for Equivariant Shape Space Learning

TL;DR

This paper introduces a novel framework for shape space learning that incorporates equivariance through frame averaging, enabling better generalization to unseen shapes and articulated poses.

Contribution

It adapts the Frame Averaging framework for efficient, expressive equivariant autoencoders, including the first fully piecewise Euclidean equivariant autoencoder.

Findings

Achieves state-of-the-art generalization on rigid shape datasets.

Significantly improves generalization to unseen articulated poses.

Uses standard training losses without additional complexity.

Abstract

The task of shape space learning involves mapping a train set of shapes to and from a latent representation space with good generalization properties. Often, real-world collections of shapes have symmetries, which can be defined as transformations that do not change the essence of the shape. A natural way to incorporate symmetries in shape space learning is to ask that the mapping to the shape space (encoder) and mapping from the shape space (decoder) are equivariant to the relevant symmetries. In this paper, we present a framework for incorporating equivariance in encoders and decoders by introducing two contributions: (i) adapting the recent Frame Averaging (FA) framework for building generic, efficient, and maximally expressive Equivariant autoencoders; and (ii) constructing autoencoders equivariant to piecewise Euclidean motions applied to different parts of the shape. To the best of our knowledge, this is the first fully piecewise Euclidean equivariant autoencoder construction. Training our framework is simple: it uses standard reconstruction losses and does not require the introduction of new losses. Our architectures are built of standard (backbone) architectures with the appropriate frame averaging to make them equivariant. Testing our framework on both rigid shapes dataset using implicit neural representations, and articulated shape datasets using mesh-based neural networks show state-of-the-art generalization to unseen test shapes, improving relevant baselines by a large margin. In particular, our method demonstrates significant improvement in generalizing to unseen articulated poses.