Paper Detail
Wenqi Jia, Zekun Li, Abhay Mittal, Chengcheng Tang, Chuan Guo, Lezi Wang, James Matthew Rehg, Lingling Tao, Size An
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
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@misc{jia2026iam,
title = {IAM: Identity-Aware Human Motion and Shape Joint Generation},
author = {Wenqi Jia and Zekun Li and Abhay Mittal and Chengcheng Tang and Chuan Guo and Lezi Wang and James Matthew Rehg and Lingling Tao and Size An},
year = {2026},
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 ofte},
url = {https://huggingface.co/papers/2604.25164},
keywords = {text-driven human motion generation, body morphology, motion dynamics, identity-aware motion generation, multimodal signals, joint motion-shape generation, motion capture datasets, in-the-wild videos, huggingface daily},
eprint = {2604.25164},
archiveprefix = {arXiv},
}
{}