Improvements on SadTalker-based Approach for ViCo Conversational Head Generation Challenge

摘要

This paper presents our solution in the ACM Multimedia ViCo 2023 Conversational Head Generation Challenge, which aims to generate vivid face-to-face conversation videos based on audio and reference images. Our approach builds upon the SadTalker framework with several improvements. Since SadTalker is already a mature and well-developed framework, consisting of multiple stages of algorithms and models, our enhancements mainly focus on the preprocessing and postprocessing stages. With our improved method, we achieved second place in both the Talking Head Generation track and the Listening Head Generation track.