• Home
  • Posts
  • CV
  • Publications

Audio Based face reenactment

 · 30 Jun 2025

added the project which I and Vishal Patil worked on, in Generative AI course. It was actually combination of two papers. We modified wav2pix to basically add lip landmarks and added losses on the lip sync to better capture the lip movements as per the audio.

Tags: computer vision, generative AI

© shweta sharma 2026
  • Created by David Darnes