Frieren: Efficient Video-to-Audio Generation Network with Rectified Flow Matching

Documenti analoghi

• MoMu-Diffusion: On Learning Long-Term Motion-Music Synchronization and Correspondence
  di: You, Fuming, et al.
  Pubblicazione: (2024)
• Towards Streaming Synchronized Spatial Audio Generation via Autoregressive Diffusion Transformer
  di: Lei, Ke, et al.
  Pubblicazione: (2026)
• Semantically consistent Video-to-Audio Generation using Multimodal Language Large Model
  di: Chen, Gehui, et al.
  Pubblicazione: (2024)
• Rhythmic Foley: A Framework For Seamless Audio-Visual Alignment In Video-to-Audio Synthesis
  di: Huang, Zhiqi, et al.
  Pubblicazione: (2024)
• SyncFlow: Toward Temporally Aligned Joint Audio-Video Generation from Text
  di: Liu, Haohe, et al.
  Pubblicazione: (2024)