IAM: Identity-Aware Human Motion and Shape Joint Generation

TL;DR

This paper introduces an identity-aware framework for human motion generation that models the influence of body morphology on motion dynamics, improving realism and consistency.

Contribution

It proposes a novel joint motion-shape generation paradigm that incorporates identity cues from multimodal signals to produce more realistic, identity-consistent human motions.

Findings

Enhanced motion realism and identity consistency demonstrated on datasets.

The model effectively modulates motion based on body shape parameters.

Maintains high motion quality while incorporating identity information.

Abstract

Recent advances in text-driven human motion generation enable models to synthesize realistic motion sequences from natural language descriptions. However, most existing approaches assume identity-neutral motion and generate movements using a canonical body representation, ignoring the strong influence of body morphology on motion dynamics. In practice, attributes such as body proportions, mass distribution, and age significantly affect how actions are performed, and neglecting this coupling often leads to physically inconsistent motions. We propose an identity-aware motion generation framework that explicitly models the relationship between body morphology and motion dynamics. Instead of relying on explicit geometric measurements, identity is represented using multimodal signals, including natural language descriptions and visual cues. We further introduce a joint motion-shape generation paradigm that simultaneously synthesizes motion sequences and body shape parameters, allowing identity cues to directly modulate motion dynamics. Extensive experiments on motion capture datasets and large-scale in-the-wild videos demonstrate improved motion realism and motion-identity consistency while maintaining high motion quality. Project page: https://vjwq.github.io/IAM