IAM: Identity-Aware Human Motion and Shape Joint Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908997278236672 |
|---|---|
| author | Jia, Wenqi Li, Zekun Mittal, Abhay Tang, Chengcheng Guo, Chuan Wang, Lezi Rehg, James Matthew Tao, Lingling An, Size |
| author_facet | Jia, Wenqi Li, Zekun Mittal, Abhay Tang, Chengcheng Guo, Chuan Wang, Lezi Rehg, James Matthew Tao, Lingling An, Size |
| contents | 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 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_25164 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | IAM: Identity-Aware Human Motion and Shape Joint Generation Jia, Wenqi Li, Zekun Mittal, Abhay Tang, Chengcheng Guo, Chuan Wang, Lezi Rehg, James Matthew Tao, Lingling An, Size Computer Vision and Pattern Recognition 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 |
| title | IAM: Identity-Aware Human Motion and Shape Joint Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.25164 |