SCAIL: Towards Studio-Grade Character Animation via In-Context Learning of 3D-Consistent Pose Representations
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912978235817984 |
|---|---|
| author | Yan, Wenhao Ye, Sheng Yang, Zhuoyi Teng, Jiayan Dong, ZhenHui Wen, Kairui Gu, Xiaotao Liu, Yong-Jin Tang, Jie |
| author_facet | Yan, Wenhao Ye, Sheng Yang, Zhuoyi Teng, Jiayan Dong, ZhenHui Wen, Kairui Gu, Xiaotao Liu, Yong-Jin Tang, Jie |
| contents | Achieving controllable character animation that meets studio-grade standards remains challenging despite recent progress. Existing approaches can transfer motion from a driving video to a reference image, but often fail to preserve structural fidelity and temporal consistency in wild scenarios involving complex motion and cross-identity animations. In this work, we present \textbf{SCAIL} (a framework toward \textbf{S}tudio-grade \textbf{C}haracter \textbf{A}nimation via \textbf{I}n-context \textbf{L}earning), which is designed to address these challenges from two key innovations. First, we propose a novel 3D pose representation, providing a robust and flexible motion signal. Second, we introduce a full-context pose injection mechanism within a diffusion-transformer, enabling effective spatio-temporal reasoning over full motion sequences. To align with studio-grade requirements, we develop a curated data pipeline ensuring both diversity and quality, and establish a comprehensive benchmark for systematic evaluation. Experiments show that \textbf{SCAIL} achieves state-of-the-art performance and advances character animation toward studio-grade controlling. Code and model are available at \href{https://github.com/zai-org/SCAIL}{zai-org/SCAIL}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_05905 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SCAIL: Towards Studio-Grade Character Animation via In-Context Learning of 3D-Consistent Pose Representations Yan, Wenhao Ye, Sheng Yang, Zhuoyi Teng, Jiayan Dong, ZhenHui Wen, Kairui Gu, Xiaotao Liu, Yong-Jin Tang, Jie Computer Vision and Pattern Recognition Achieving controllable character animation that meets studio-grade standards remains challenging despite recent progress. Existing approaches can transfer motion from a driving video to a reference image, but often fail to preserve structural fidelity and temporal consistency in wild scenarios involving complex motion and cross-identity animations. In this work, we present \textbf{SCAIL} (a framework toward \textbf{S}tudio-grade \textbf{C}haracter \textbf{A}nimation via \textbf{I}n-context \textbf{L}earning), which is designed to address these challenges from two key innovations. First, we propose a novel 3D pose representation, providing a robust and flexible motion signal. Second, we introduce a full-context pose injection mechanism within a diffusion-transformer, enabling effective spatio-temporal reasoning over full motion sequences. To align with studio-grade requirements, we develop a curated data pipeline ensuring both diversity and quality, and establish a comprehensive benchmark for systematic evaluation. Experiments show that \textbf{SCAIL} achieves state-of-the-art performance and advances character animation toward studio-grade controlling. Code and model are available at \href{https://github.com/zai-org/SCAIL}{zai-org/SCAIL}. |
| title | SCAIL: Towards Studio-Grade Character Animation via In-Context Learning of 3D-Consistent Pose Representations |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.05905 |