A functional skeleton transfer

TL;DR

This paper introduces a novel functional approach for transferring skeletons between 3D shapes that requires limited supervision and is invariant to geometry discretization, improving flexibility and efficiency in rigging tasks.

Contribution

It proposes a new functional regressor representation for skeleton transfer that reduces supervision needs and handles different geometries without full shape matching.

Findings

The method achieves high accuracy in skeleton transfer across diverse shapes.

It demonstrates computational efficiency and robustness to shape discretization.

Preliminary results show potential for complete rigging transfer applications.

Abstract

The animation community has spent significant effort trying to ease rigging procedures. This is necessitated because the increasing availability of 3D data makes manual rigging infeasible. However, object animations involve understanding elaborate geometry and dynamics, and such knowledge is hard to infuse even with modern data-driven techniques. Automatic rigging methods do not provide adequate control and cannot generalize in the presence of unseen artifacts. As an alternative, one can design a system for one shape and then transfer it to other objects. In previous work, this has been implemented by solving the dense point-to-point correspondence problem. Such an approach requires a significant amount of supervision, often placing hundreds of landmarks by hand. This paper proposes a functional approach for skeleton transfer that uses limited information and does not require a complete match between the geometries. To do so, we suggest a novel representation for the skeleton properties, namely the functional regressor, which is compact and invariant to different discretizations and poses. We consider our functional regressor a new operator to adopt in intrinsic geometry pipelines for encoding the pose information, paving the way for several new applications. We numerically stress our method on a large set of different shapes and object classes, providing qualitative and numerical evaluations of precision and computational efficiency. Finally, we show a preliminar transfer of the complete rigging scheme, introducing a promising direction for future explorations.