Saved in:
Bibliographic Details
Main Authors: Chen, Liuhan, Zhong, Lei, Wang, Jiewei, Shuai, Qin, Yuan, Li, Fan, Leidong, Li, Qing, Liu, Kanglin
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.15497
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911698200297472
author Chen, Liuhan
Zhong, Lei
Wang, Jiewei
Shuai, Qin
Yuan, Li
Fan, Leidong
Li, Qing
Liu, Kanglin
author_facet Chen, Liuhan
Zhong, Lei
Wang, Jiewei
Shuai, Qin
Yuan, Li
Fan, Leidong
Li, Qing
Liu, Kanglin
contents We study the problem of directly deriving an initial human reenactment from a monocular video of a non-human character. Our goal is not to reconstruct the source character itself but to reinterpret its motion as a plausible and editable human performance for downstream animation authoring. This task is challenging because existing video-based motion capture methods are largely restricted to human-centric structural spaces, while motion retargeting methods typically require structured 3D source motions and known source topologies. Our key insight is that sparse local articulated motion cues can preserve essential dynamics across large structural differences, providing a stable bridge from character video to human reenactment. Based on this observation, we propose AnyAct, which formulates character-video-driven human reenactment as conditional human motion generation from transferable sparse local 2D articulated motion. To make this practical, we introduce three key designs: human-motion-only supervision via augmented 3D-to-2D projection, progressive 3D-to-2D training to alleviate conditioning ambiguity, and global-local motion decoupling for reliable local motion control. We further construct a benchmark primarily covering diverse non-human character videos. Experiments on the benchmark show that AnyAct produces high-fidelity initial human reenactments that preserve the essential dynamics of the characters in reference videos, and further ablation studies validate the effectiveness of its core designs.
format Preprint
id arxiv_https___arxiv_org_abs_2605_15497
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle AnyAct: Towards Human Reenactment of Character Motion From Video
Chen, Liuhan
Zhong, Lei
Wang, Jiewei
Shuai, Qin
Yuan, Li
Fan, Leidong
Li, Qing
Liu, Kanglin
Computer Vision and Pattern Recognition
Graphics
We study the problem of directly deriving an initial human reenactment from a monocular video of a non-human character. Our goal is not to reconstruct the source character itself but to reinterpret its motion as a plausible and editable human performance for downstream animation authoring. This task is challenging because existing video-based motion capture methods are largely restricted to human-centric structural spaces, while motion retargeting methods typically require structured 3D source motions and known source topologies. Our key insight is that sparse local articulated motion cues can preserve essential dynamics across large structural differences, providing a stable bridge from character video to human reenactment. Based on this observation, we propose AnyAct, which formulates character-video-driven human reenactment as conditional human motion generation from transferable sparse local 2D articulated motion. To make this practical, we introduce three key designs: human-motion-only supervision via augmented 3D-to-2D projection, progressive 3D-to-2D training to alleviate conditioning ambiguity, and global-local motion decoupling for reliable local motion control. We further construct a benchmark primarily covering diverse non-human character videos. Experiments on the benchmark show that AnyAct produces high-fidelity initial human reenactments that preserve the essential dynamics of the characters in reference videos, and further ablation studies validate the effectiveness of its core designs.
title AnyAct: Towards Human Reenactment of Character Motion From Video
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2605.15497