JD Cloud Developers

Jul 2, 2025 · Artificial Intelligence

How JoyGen Achieves High‑Quality Audio‑Driven 3D Talking‑Face Video Editing

JoyGen introduces a two‑stage framework that combines 3D morphable model reconstruction with audio‑driven lip motion generation and depth‑aware visual synthesis, delivering precise audio‑lip synchronization and superior visual quality on both the HDTF benchmark and a newly built high‑resolution Chinese talking‑face dataset.