AlignHuman: Improving Motion and Fidelity via Timestep-Segment Preference Optimization for Audio-Driven Human Animation

Documenti analoghi

• InterActHuman: Multi-Concept Human Animation with Layout-Aligned Audio Conditions
  di: Wang, Zhenzhi, et al.
  Pubblicazione: (2025)
• OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models
  di: Lin, Gaojie, et al.
  Pubblicazione: (2025)
• OmniHuman-1.5: Instilling an Active Mind in Avatars via Cognitive Simulation
  di: Jiang, Jianwen, et al.
  Pubblicazione: (2025)
• FantasyTalking2: Timestep-Layer Adaptive Preference Optimization for Audio-Driven Portrait Animation
  di: Wang, MengChao, et al.
  Pubblicazione: (2025)
• Loopy: Taming Audio-Driven Portrait Avatar with Long-Term Motion Dependency
  di: Jiang, Jianwen, et al.
  Pubblicazione: (2024)