IAM: Identity-Aware Human Motion and Shape Joint Generation

arXiv:2604.25164v1 Announce Type: new 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

Related

• LLaMo: Scaling Pretrained Language Models for Unified Motion Understanding and Generation with Continuous Autoregressive Tokens
• From Diffusion to Flow: Efficient Motion Generation in MotionGPT3
• Re^2MoGen: Open-Vocabulary Motion Generation via LLM Reasoning and Physics-Aware Refinement
• A Unified Conditional Flow for Motion Generation, Editing, and Intra-Structural Retargeting

Source: arXiv cs.CV | 2026-04-29