Open access
Aug 2026
AnyTalk: Speech Animation for Arbitrary Characters Leveraging a Video Generation Model.
AnyTalk enables lip-synced animations across diverse face meshes and blendshape configurations, significantly reducing manual effort and data requirements and enhances usability by distilling AnyTalk into a streamlined network, $\text{AnyTalk}_{RT}$, thereby enabling real-time performance.
Kwan Yun, Serin Yoon, Sun-Jin Jung et al.
· IEEE Transactions on Visuali... · 0 citations