IAM: Identity-Aware Human Motion and Shape Joint Generation

2026-04-27

AI Summary

Existing text-driven human motion generation methods often neglect the influence of body morphology on motion dynamics, leading to physically implausible results. This work proposes the first identity-aware joint generation framework that integrates textual and visual cues to construct a multimodal identity representation, simultaneously synthesizing motion sequences and body shape parameters. By directly modulating motion dynamics with identity characteristics, the approach implicitly captures the coupling between body morphology and movement without requiring explicit geometric measurements. Experiments demonstrate that the proposed method significantly enhances motion realism, identity consistency, and overall quality on both motion capture datasets and large-scale in-the-wild videos.

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

Problem

• human motion generation
• body morphology
• motion dynamics
• identity-aware
• motion-identity consistency

Innovation

• identity-aware motion generation
• motion-shape joint generation
• body morphology
• multimodal identity representation
• text-driven human motion