ONE-SHOT: Compositional Human-Environment Video Synthesis via Spatial-Decoupled Motion Injection and Hybrid Context Integration

Documenti analoghi

• DISPLAY: Directable Human-Object Interaction Video Generation via Sparse Motion Guidance and Multi-Task Auxiliary
  di: Guan, Jiazhi, et al.
  Pubblicazione: (2026)
• GestureHYDRA: Semantic Co-speech Gesture Synthesis via Hybrid Modality Diffusion Transformer and Cascaded-Synchronized Retrieval-Augmented Generation
  di: Yang, Quanwei, et al.
  Pubblicazione: (2025)
• InterDyad: Interactive Dyadic Speech-to-Video Generation by Querying Intermediate Visual Guidance
  di: Pan, Dongwei, et al.
  Pubblicazione: (2026)
• Cosh-DiT: Co-Speech Gesture Video Synthesis via Hybrid Audio-Visual Diffusion Transformers
  di: Sun, Yasheng, et al.
  Pubblicazione: (2025)
• TALK-Act: Enhance Textural-Awareness for 2D Speaking Avatar Reenactment with Diffusion Model
  di: Guan, Jiazhi, et al.
  Pubblicazione: (2024)