Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.21581 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910206811701248 |
|---|---|
| author | Hu, Yingcheng Gong, Haowen Yang, Chuanguang An, Zhulin Xu, Yongjun Liu, Songhua |
| author_facet | Hu, Yingcheng Gong, Haowen Yang, Chuanguang An, Zhulin Xu, Yongjun Liu, Songhua |
| contents | Pose-guided human image animation aims to synthesize realistic videos of a reference character driven by a sequence of poses. While diffusion-based methods have achieved remarkable success, most existing approaches are limited to single-character animation. We observe that naively extending these methods to multi-character scenarios often leads to identity confusion and implausible occlusions between characters. To address these challenges, in this paper, we propose an extensible multi-character image animation framework built upon modern Diffusion Transformers (DiTs) for video generation. At its core, our framework introduces two novel components-Identifier Assigner and Identifier Adapter - which collaboratively capture per-person positional cues and inter-person spatial relationships. This mask-driven scheme, along with a scalable training strategy, not only enhances flexibility but also enables generalization to scenarios with more characters than those seen during training. Remarkably, trained on only a two-character dataset, our model generalizes to multi-character animation while maintaining compatibility with single-character cases. Extensive experiments demonstrate that our approach achieves state-of-the-art performance in multi-character image animation, surpassing existing diffusion-based baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_21581 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MultiAnimate: Pose-Guided Image Animation Made Extensible Hu, Yingcheng Gong, Haowen Yang, Chuanguang An, Zhulin Xu, Yongjun Liu, Songhua Computer Vision and Pattern Recognition Pose-guided human image animation aims to synthesize realistic videos of a reference character driven by a sequence of poses. While diffusion-based methods have achieved remarkable success, most existing approaches are limited to single-character animation. We observe that naively extending these methods to multi-character scenarios often leads to identity confusion and implausible occlusions between characters. To address these challenges, in this paper, we propose an extensible multi-character image animation framework built upon modern Diffusion Transformers (DiTs) for video generation. At its core, our framework introduces two novel components-Identifier Assigner and Identifier Adapter - which collaboratively capture per-person positional cues and inter-person spatial relationships. This mask-driven scheme, along with a scalable training strategy, not only enhances flexibility but also enables generalization to scenarios with more characters than those seen during training. Remarkably, trained on only a two-character dataset, our model generalizes to multi-character animation while maintaining compatibility with single-character cases. Extensive experiments demonstrate that our approach achieves state-of-the-art performance in multi-character image animation, surpassing existing diffusion-based baselines. |
| title | MultiAnimate: Pose-Guided Image Animation Made Extensible |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.21581 |