EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

A Unified Conditional Flow for Motion Generation, Editing, and Intra-Structural Retargeting

Junlin Li, Xinhao Song, Siqi Wang, Haibin Huang, Yili Zhao

ACM Transactions on Graphics · 09.11.2026 · 45 (6) · 1-12

DOI: 10.1145/3842508 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Graphics, online erschienen am 09.11.2026. Verfasst von Junlin Li und 4 weiteren Autor:innen. Die Arbeit nennt 70 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Text-driven motion editing and intra-structural retargeting, where skeletons share topology but may differ in bone lengths and rest pose, are traditionally handled by fragmented pipelines with incompatible inputs and representations: editing relies on specialized generative steering, while retargeting is deferred to geometric post-processing. We present a unified conditional-flow framework that casts generation, semantic editing, and intra-structural retargeting as condition-modulated transport within one text- and skeleton-conditioned rectified-flow model. Under this formulation, editing changes the semantic condition while preserving skeletal structure, whereas retargeting changes the skeletal condition while preserving motion semantics. This makes FlowEdit-style transport a unified inference rule for motion manipulation rather than a task-specific editor. To instantiate this for articulated 3D motion, we develop a text- and skeleton-conditioned rectified-flow transformer. The model uses per-joint tokenization and explicit joint self-attention to capture spatial kinematic dependencies. We further inject text conditions at both joint and frame levels, while residual multi-condition classifier-free guidance balances text adherence and skeletal conformity. Experiments on SnapMoGen and a multi-character Mixamo subset show that one trained model supports text-to-motion generation, zero-shot editing, and zero-shot intra-structural retargeting without task-specific fine-tuning. This unified framework replaces separate pipelines with a single conditional motion transport model while keeping the same-topology retargeting scope explicit.

Zitieren

APA

Li, J., Song, X., Wang, S., Huang, H., & Zhao, Y. (2026). A Unified Conditional Flow for Motion Generation, Editing, and Intra-Structural Retargeting. ACM Transactions on Graphics, 45(6), 1-12. https://doi.org/10.1145/3842508

Vancouver

Li J, Song X, Wang S, Huang H, Zhao Y. A Unified Conditional Flow for Motion Generation, Editing, and Intra-Structural Retargeting. ACM Transactions on Graphics. 2026;45(6):1-12. doi:10.1145/3842508

BibTeX
@article{Li2026,
  author = {Li, Junlin and Song, Xinhao and Wang, Siqi and Huang, Haibin and Zhao, Yili},
  title = {A Unified Conditional Flow for Motion Generation, Editing, and Intra-Structural Retargeting},
  journal = {ACM Transactions on Graphics},
  year = {2026},
  volume = {45},
  number = {6},
  pages = {1--12},
  doi = {10.1145/3842508}
}
Kostenlos starten →