Metraipolis › archive › dc_27cfa9add643

WeLike2Party! In-Context Motion Transfer for Multi-Human Image Animation — arXiv:2609.36937

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.36937
License (as archived)
CC0-1.0
Archived
2026-10-07T16:26:32.762Z
SHA-256 of the archived text
5f47e2bc27c75b1bf6d1869e6414b5755adc87045974fbdf01a1f0b3503afabd
Stable URL of this page
https://metraipolis.com/documento/dc_27cfa9add643

How to cite

WeLike2Party! In-Context Motion Transfer for Multi-Human Image Animation — arXiv:2609.36937 — arXiv (en), https://arxiv.org/abs/2609.36937 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_27cfa9add643 (Metraipolis archive dc_27cfa9add643, sha256 5f47e2bc27c75b1bf6d1869e6414b5755adc87045974fbdf01a1f0b3503afabd)
BibTeX
@misc{dc27cfa9add643,
  title = {WeLike2Party! In-Context Motion Transfer for Multi-Human Image Animation — arXiv:2609.36937},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.36937},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_27cfa9add643; sha256 5f47e2bc27c75b1bf6d1869e6414b5755adc87045974fbdf01a1f0b3503afabd},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36937. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Human image animation aims to transfer motion from a driving video to subjects in a reference image. Despite remarkable progress in video generation, achieving high-fidelity animation of multiple interacting subjects remains a challenge. Many existing approaches rely on explicit motion representations such as 2D skeletons or parametric body meshes and struggle to preserve identity-motion binding under inter-person occlusion. To address this limitation, we propose WeLike2Party, a multi-human animation framework built on direct in-context video conditioning without explicit pose or mesh extraction at inference. We further introduce Reference Asymmetric RoPE Conditioning to preserve fine-grained appearance details, and Identity Binding Supervision to associate each reference identity with its intended motion trajectory. To support cross-identity training, we construct MotionTwin, a large-scale synthetic dataset comprising 14.4K cross-identity video pairs with shared subject and camera motions, totaling 84.3 hours of photorealistic video. We additionally present MotionTwin-Bench, a cross-identity benchmark specifically designed to evaluate subject-level visual fidelity and identity-motion binding. Extensive experiments on MotionTwin-Bench and real-world videos demonstrate that WeLike2Party outperforms recent state-of-the-art methods in subject-level visual fidelity, identity-motion binding, and overall perceptual quality, particularly in multi-person interactions with substantial occlusion.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.36937 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T15:54:53.908Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).