Recent progress in video diffusion models has markedly advanced character animation, which synthesizes motioned videos by animating a static identity image according to a driving video. Explicit methods represent motion using skeleton, DWPose or other explicit structured signals, but struggle to handle spatial mismatches and varying body scales. %proportions. Implicit methods, on the other hand, capture high-level implicit motion semantics directly from the driving video, but suffer from identity leakage and entanglement between motion and appearance. To address the above challenges, we propose a novel implicit motion representation that compresses per-frame motion into compact 1D motion tokens. This design relaxes strict spatial constraints inherent in 2D representations and effectively prevents identity information leakage from the motion video. Furthermore, we design a temporally consistent mask token-based retargeting module that enforces a temporal training bottleneck, mitigating interference from the source images' motion and improving retargeting consistency. Our methodology employs a three-stage training strategy to enhance the training efficiency and ensure high fidelity. Extensive experiments demonstrate that our implicit motion representation and the propose IM-Animation's generative capabilities are achieve superior or competitive performance compared with state-of-the-art methods.
@article{arxiv.2602.07498,
title = {IM-Animation: An Implicit Motion Representation for Identity-decoupled Character Animation},
author = {Zhufeng Xu and Xuan Gao and Feng-Lin Liu and Haoxian Zhang and Zhixue Fang and Yu-Kun Lai and Xiaoqiang Liu and Pengfei Wan and Lin Gao},
journal= {arXiv preprint arXiv:2602.07498},
year = {2026}
}