EUVIMEDEUVIMED entdecken
Crossref

Adaptive Reference Refinement for Physics‐based Motion Retargeting

Seungbin Jeong, Young Min Kim

Computer Graphics Forum · 13.11.2026

DOI: 10.1111/cgf.70610 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computer Graphics Forum, online erschienen am 13.11.2026. Verfasst von Seungbin Jeong und 1 weiteren Autor:innen. Die Arbeit nennt 49 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Physics‐based character control for high‐dimensional humanoid motion requires reference motion‐capture data to guide stable training of the reinforcement learning (RL) policy. However, the motion dynamics of the reference trajectory and the control target may differ in terms of mass, torque limits, and morphology. Conventional retargeting compensates for offsets based on kinematic structure, without considering real‐world dynamics such as gravity, contact forces, and torque control, and the resulting motion fails to robustly guide policy training for the control target. We propose a motion refinement network that learns to automatically adjust retargeted results to be physically plausible, reflecting the non‐linear relationship arising from the dynamic interplay between different skeleton structures and the environment. As the policy directly learns to track refined references in physical simulation, the resulting motions are free of physical artifacts, such as foot sliding, ground penetration, and implausible joint configurations, which are frequently observed in retargeting results applying inverse kinematics. While concurrent training of motion refinement and the RL policy often diverges, we introduce a warming‐up scheme that initially trains the policy using only a fixed refinement network, then gradually introduces refinement offsets. The offsets are then selectively applied to the retargeted motion only when a substantial deviation is required. Experiments show that our method consistently improves physical plausibility over retargeting baselines using inverse kinematics, and further improves tracking performance particularly when combined with baselines that produce reasonably reliable initial references. Our method also generalizes robustly to retargeting across extremely different morphologies and physical properties, including dramatic changes in limb lengths and carrying of excessively heavy payloads.

Zitieren

APA

Jeong, S., & Kim, Y. M. (2026). Adaptive Reference Refinement for Physics‐based Motion Retargeting. Computer Graphics Forum. https://doi.org/10.1111/cgf.70610

Vancouver

Jeong S, Kim YM. Adaptive Reference Refinement for Physics‐based Motion Retargeting. Computer Graphics Forum. 2026. doi:10.1111/cgf.70610

BibTeX
@article{Jeong2026,
  author = {Jeong, Seungbin and Kim, Young Min},
  title = {Adaptive Reference Refinement for Physics‐based Motion Retargeting},
  journal = {Computer Graphics Forum},
  year = {2026},
  doi = {10.1111/cgf.70610}
}
Kostenlos starten →