| | --- |
| | license: mit |
| | pipeline_tag: image-to-video |
| | library_name: diffusers |
| | --- |
| | |
| | # CharacterShot: Controllable and Consistent 4D Character Animation |
| |
|
| | [CharacterShot](https://arxiv.org/abs/2508.07409) is a controllable and consistent 4D character animation framework that enables any individual designer to create dynamic 3D characters from a single reference character image and a 2D pose sequence. |
| |
|
| | - **Paper:** [CharacterShot: Controllable and Consistent 4D Character Animation](https://arxiv.org/abs/2508.07409) |
| | - **Code:** [GitHub Repository](https://github.com/Jeoyal/CharacterShot) |
| | - **Authors:** [Junyao Gao](https://huggingface.co/Gaojunyao), [Jiaxing Li](https://huggingface.co/LiJiaxing), Wenran Liu, [Yanhong Zeng](https://huggingface.co/zengyh1900), Fei Shen, Kai Chen, Yanan Sun, Cairong Zhao |
| |
|
| | ## Introduction |
| |
|
| | CharacterShot begins by pretraining a powerful 2D character animation model based on a DiT-based image-to-video model (CogVideoX). It lifts the animation model from 2D to 3D through introducing dual-attention module together with camera prior to generate multi-view videos with spatial-temporal and spatial-view consistency. Finally, it employs a novel neighbor-constrained 4D gaussian splatting optimization on these multi-view videos, resulting in continuous and stable 4D character representations. |
| |
|
| | ## Citation |
| |
|
| | ```bibtex |
| | @article{gao2025charactershot, |
| | title={CharacterShot: Controllable and Consistent 4D Character Animation}, |
| | author={Gao, Junyao and Li, Jiaxing and Liu, Wenran and Zeng, Yanhong and Shen, Fei and Chen, Kai and Sun, Yanan and Zhao, Cairong}, |
| | journal={arXiv preprint arXiv:2508.07409}, |
| | year={2025}, |
| | } |
| | ``` |
| |
|
| | ## Acknowledgements |
| | The code is built upon [CogVideo](https://github.com/THUDM/CogVideo). |
