Oct 2026· Mathematical Modeling and Algorithm Application· 0 citations· 27 references
TL;DR
This paper systematically reviews representative literature on motion capture and retargeting, organized into five categories following the complete industrial workflow: multi-modal motion acquisition and preprocessing, cross-skeleton shape-adaptive retargeting, AI-assisted motion generation, physically constrained interactive retargeting, and end-to-end integrated pipelines with cross-domain applications.
Abstract
Motion capture serves as the core data acquisition method for character animation, while motion retargeting enables the cross-character reuse of captured motion sequences. The integrated pipeline of capture and retargeting has become the mainstream production workflow for games, VR, and digital human creation. Traditional geometric retargeting methods are prone to foot sliding, ground penetration, and loss of contact semantics when processing motion capture data with occlusion noise, whereas recent deep learning and physical optimization algorithms have significantly improved the naturalness of retargeted motions. This paper systematically reviews representative literature on motion capture and retargeting, organized into five categories following the complete industrial workflow: multi-modal motion acquisition and preprocessing, cross-skeleton shape-adaptive retargeting, AI-assisted motion generation, physically constrained interactive retargeting, and end-to-end integrated pipelines with cross-domain applications. For each category, we elaborate on core technical schemes, inherent limitations, and typical experimental outcomes with standard citations. This survey provides systematic literature support for researchers engaged in motion capture and retargeting animation.
Video editing models achieve strong performance in modifying appearance, backgrounds, styles, and motions, empowered by large-scale training data. Beyond general scenarios, professional motions are significant in performance, sports, and martial arts. This paper focuses on professional motion editing, which involves fi...
Si-Yi Qian, Han-Qing Yang, Wei-Huang Lin et al.· 0 citations
This work synthesizes methodologies to optimize the responsiveness of AI-based MoCap systems within contemporary real-time software architectures and focuses on integrating 3D human pose estimation (HPE) into standard graphics engines.
Recent advances in 2D and 3D generative modeling have paved the way for 4D generation. However, existing methods predominantly focus on text-to-4D generation, emphasizing temporal smoothness and spatial consistency while often neglecting precise motion control. Furthermore, due to the inherent ambiguity of text descrip...
Run-Xin Liu, Yang Chen, Ying-Wei Pan et al.· IEEE Transactions on Pattern...· 0 citations
While large-scale human motion capture datasets provide a rich source of demonstrations for humanoid robot learning, retargeting the diverse motions to different humanoid robots remains a nontrivial challenge. Existing kinodynamic trajectory optimization pipelines are computationally expensive and often require manual...
Daniel Marew, Sangjun Park, Nisal Perera et al.· 0 citations
AnimateCanvas is proposed, a model that supports cue-conditioned implicit motion planning to faithfully and coherently connect all cues, dense or sparse, full or partial, into one full-body motion sequence, and achieves state-of-the-art results in temporal completion, spatial control, sequential generation, language-gu...
Ze-Yu Ling, Di Kang, Qing Shuai et al.· 0 citations
Generating high-quality and controllable camera motion is essential for AI-assisted cinematography, video synthesis, and 3D scene understanding. We introduce TKCAM, a Text- and Keyframe-conditioned CAMera-motion synthesis framework based on generative masked modeling. We represent camera dynamics using a 12-dimensional...
Hao-Zhe Yang, Zhiyang Dou, Ze-Kai Gu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.