ReConForM : Real-time Contact-aware Motion Retargeting for more Diverse Character Morphologies

TL;DR

ReConForM introduces a real-time, contact-aware motion retargeting method that adapts to diverse character morphologies by using a low-dimensional mesh embedding and an adaptive feature selection algorithm, improving contact preservation and motion quality.

Contribution

The paper presents a novel low-dimensional mesh embedding and an adaptive feature weighting algorithm for real-time, contact-aware motion retargeting across diverse character shapes.

Findings

Achieves real-time retargeting for various characters.

Improves contact accuracy over state-of-the-art methods.

Enhances motion smoothness and semantic preservation.

Abstract

Preserving semantics, in particular in terms of contacts, is a key challenge when retargeting motion between characters of different morphologies. Our solution relies on a low-dimensional embedding of the character's mesh, based on rigged key vertices that are automatically transferred from the source to the target. Motion descriptors are extracted from the trajectories of these key vertices, providing an embedding that contains combined semantic information about both shape and pose. A novel, adaptive algorithm is then used to automatically select and weight the most relevant features over time, enabling us to efficiently optimize the target motion until it conforms to these constraints, so as to preserve the semantics of the source motion. Our solution allows extensions to several novel use-cases where morphology and mesh contacts were previously overlooked, such as multi-character retargeting and motion transfer on uneven terrains. As our results show, our method is able to achieve real-time retargeting onto a wide variety of characters. Extensive experiments and comparison with state-of-the-art methods using several relevant metrics demonstrate improved results, both in terms of motion smoothness and contact accuracy.