titleMotion Beyond Morphology: Bootstrapping Cross-Category Motion Transfer from Abstract Motion Representations
authorsZhixue Fang, Zhimin Zhang, Bi'an Du, Zijie Meng, Yan Zhou, Wei Hu, Guoxin Zhang, Pengfei Wan, Kun Gai
date2026-08-03
venuearXiv (preprint, not peer reviewed)
idarXiv:2608.01628
affiliationKlingAI Research
upvotes16 (Hugging Face Daily Papers, 2026-11-01)
linksabs pdf hf code
abstractVideo motion transfer aims to animate a target object using dynamics from a reference video. Existing formulations largely rely on fixed structural correspondence, which becomes ill-defined when reference and target objects differ substantially in morphology, articulation, or deformation mechanisms. We introduce Motion Beyond Morphology, a perspective that seeks to transfer motion beyond fixed structural correspondence, by preserving dynamics that remain meaningful across different target morphologies. To realize this, we propose a two-stage framework. Stage~I learns complementary multi-granularity abstract motion views and uses them to bootstrap cross-category video pairs that preserve transferable dynamics across diverse morphologies. Stage~II internalizes this supervision into direct reference-video-conditioned generation, removing the need for explicit motion extraction at inference. We further introduce OpenVMT-Dataset and OpenVMT-Bench for training and evaluating image- and text-conditioned motion transfer across Same, Near, and Far category gaps, and plan to release both upon acceptance. Extensive experiments demonstrate state-of-the-art motion fidelity and target preservation. Project page: https://miniz233.github.io/MotionBeyondMorphology/

cite

@misc{fang2026motion,
  title={Motion Beyond Morphology: Bootstrapping Cross-Category Motion Transfer from Abstract Motion Representations},
  author={Zhixue Fang and Zhimin Zhang and Bi'an Du and Zijie Meng and Yan Zhou and Wei Hu and Guoxin Zhang and Pengfei Wan and Kun Gai},
  year={2026},
  eprint={2608.01628},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2608.01628}
}