Artificial Intelligence · 28.08.2026, 07:17 UTC
A Unified Conditional Flow for Motion Generation, Editing, and Intra-Structural Retargeting
| Schweregrad | info |
|---|---|
| Kategorie | Artificial Intelligence |
| Quelle | arXiv cs.AI ↗ |
| Veröffentlicht | 28.08.2026 UTC |
Sicherheitsmeldung mit Schweregrad noch nicht bewertet. Technische Details im Tab „Originaltext“; empfohlene Schritte in der Checkliste.
arXiv:2604.13427v2 Announce Type: replace-cross Abstract: 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 …
Maßnahmen
⬇ Als MarkdownVerwandte Beiträge
- info Scaling Model-Generated Distillation Data Can Make Latent Teacher Traits More Recoverable
- info A Layer Importance Metric for Quantization Accounting for the Speed-Quality Trade-off in Autoregressive Models
- info Mitigating Strong-Modality Collapse in Multimodal Learning via Inverted Asymmetric Fusion
- info When Is the Sharp Covariance Envelope Tight? Feature-Only Geometry for Volume-Sampled Least Squares