HM-Talker: Hybrid Motion Modeling for High-Fidelity Talking Head Synthesis

Documenti analoghi

• M2DAO-Talker: Harmonizing Multi-granular Motion Decoupling and Alternating Optimization for Talking-head Generation
  di: Jiang, Kui, et al.
  Pubblicazione: (2025)
• MoDiTalker: Motion-Disentangled Diffusion Model for High-Fidelity Talking Head Generation
  di: Kim, Seyeon, et al.
  Pubblicazione: (2024)
• Learning from History: Task-agnostic Model Contrastive Learning for Image Restoration
  di: Wu, Gang, et al.
  Pubblicazione: (2023)
• Boosting All-in-One Image Restoration via Self-Improved Privilege Learning
  di: Wu, Gang, et al.
  Pubblicazione: (2025)
• DAE-Talker: High Fidelity Speech-Driven Talking Face Generation with Diffusion Autoencoder
  di: Du, Chenpeng, et al.
  Pubblicazione: (2023)