MAMM: Motion Control via Metric-Aligning Motion Matching

TL;DR

MAMM introduces a novel motion control method that aligns motion sequences with arbitrary control signals using within-domain distance metrics, eliminating the need for paired data or manual mappings.

Contribution

The paper presents a new approach for motion alignment that relies solely on within-domain distances, enabling flexible control without annotated datasets or training.

Findings

Effective alignment of motion with sketches, labels, audio, and other motions.

No need for paired or annotated datasets for motion control.

Demonstrated practical applications in efficient motion control.

Abstract

We introduce a novel method for controlling a motion sequence using an arbitrary temporal control sequence using temporal alignment. Temporal alignment of motion has gained significant attention owing to its applications in motion control and retargeting. Traditional methods rely on either learned or hand-craft cross-domain mappings between frames in the original and control domains, which often require large, paired, or annotated datasets and time-consuming training. Our approach, named Metric-Aligning Motion Matching, achieves alignment by solely considering within-domain distances. It computes distances among patches in each domain and seeks a matching that optimally aligns the two within-domain distances. This framework allows for the alignment of a motion sequence to various types of control sequences, including sketches, labels, audio, and another motion sequence, all without the need for manually defined mappings or training with annotated data. We demonstrate the effectiveness of our approach through applications in efficient motion control, showcasing its potential in practical scenarios.