| license: mit | |
| library_name: diffusers | |
| pipeline_tag: image-to-video | |
| tags: | |
| - character-animation | |
| - 4d | |
| - image-to-video | |
| --- | |
| # 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 the creation of dynamic 3D characters (i.e., 4D character animation) 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) | |
| - **Repository:** [https://github.com/Jeoyal/CharacterShot](https://github.com/Jeoyal/CharacterShot) | |
| ## Introduction | |
| CharacterShot utilizes a powerful 2D character animation model based on a DiT image-to-video architecture. It lifts these animations to 3D using dual-attention modules and camera priors to ensure spatial-temporal and spatial-view consistency. The final representation is optimized using neighbor-constrained 4D Gaussian Splatting, resulting in stable and continuous character representations. | |
| The model was trained on **Character4D**, a large-scale dataset containing 13,115 unique characters with diverse appearances and motions. | |
| ## 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). |