Zero-shot High-fidelity and Pose-controllable Character Animation
Zhu, Bingwen, Wang, Fanyi, Lu, Tianyi, Liu, Peng, Su, Jingwen, Liu, Jinxiu, Zhang, Yanhao, Wu, Zuxuan, Qi, Guo-Jun, Jiang, Yu-Gang
–arXiv.org Artificial Intelligence
Image-to-video (I2V) generation aims to create a video sequence from a single image, which requires high temporal coherence and visual fidelity. However, existing approaches suffer from inconsistency of character appearances and poor preservation of fine details. Moreover, they require a large amount of video data for training, which can be computationally demanding. To address these limitations, we propose PoseAnimate, a novel zero-shot I2V framework for character animation. PoseAnimate contains three key components: 1) a Pose-Aware Control Module (PACM) that incorporates diverse pose signals into text embeddings, to preserve character-independent content and maintain precise alignment of actions. 2) a Dual Consistency Attention Module (DCAM) that enhances temporal consistency and retains character identity and intricate background details. 3) a Mask-Guided Decoupling Module (MGDM) that refines distinct feature perception abilities, improving animation fidelity by decoupling the character and background. We also propose a Pose Alignment Transition Algorithm (PATA) to ensure smooth action transition. Extensive experiment results demonstrate that our approach outperforms the state-of-the-art training-based methods in terms of character consistency and detail fidelity. Moreover, it maintains a high level of temporal coherence throughout the generated animations.
arXiv.org Artificial Intelligence
Jun-5-2024
- Genre:
- Research Report > New Finding (0.34)
- Technology:
- Information Technology
- Artificial Intelligence
- Machine Learning > Neural Networks (1.00)
- Natural Language (1.00)
- Vision (1.00)
- Graphics > Animation (1.00)
- Artificial Intelligence
- Information Technology