MotionDuet: Dual-Conditioned 3D Human Motion Generation with Video-Regularized Text Learning

Documenti analoghi

• AnchorRoute: Human Motion Synthesis with Interval-Routed Sparse Contro
  di: Fang, Pengcheng, et al.
  Pubblicazione: (2026)
• UMo: Unified Sparse Motion Modeling for Real-Time Co-Speech Avatars
  di: Zhan, Xiaoyu, et al.
  Pubblicazione: (2026)
• MOGO: Residual Quantized Hierarchical Causal Transformer for High-Quality and Real-Time 3D Human Motion Generation
  di: Fu, Dongjie, et al.
  Pubblicazione: (2025)
• PartMotionEdit: Fine-Grained Text-Driven 3D Human Motion Editing via Part-Level Modulation
  di: Yang, Yujie, et al.
  Pubblicazione: (2025)
• FlowMotion: Target-Predictive Conditional Flow Matching for Jitter-Reduced Text-Driven Human Motion Generation
  di: Cuba, Manolo Canales, et al.
  Pubblicazione: (2025)