YudongGuo/AD-NeRF
A PyTorch implementation of AD-NeRF that synthesizes talking head videos from audio using neural radiance fields.
Not currently ranked — collecting fresh signals.
star history
This repository provides a PyTorch implementation of a neural radiance field system for audio-driven talking head synthesis. The system trains separate NeRF models for head and torso regions, conditioning the generation on audio features to produce synchronized talking head videos. It was published at ICCV 2021.
Frequently asked
- What is YudongGuo/AD-NeRF?
- A PyTorch implementation of AD-NeRF that synthesizes talking head videos from audio using neural radiance fields.
- Is AD-NeRF open source?
- Yes — YudongGuo/AD-NeRF is open source, released under the MIT license.
- What language is AD-NeRF written in?
- YudongGuo/AD-NeRF is primarily written in Python.
- How popular is AD-NeRF?
- YudongGuo/AD-NeRF has 1.1k stars on GitHub.
- Where can I find AD-NeRF?
- YudongGuo/AD-NeRF is on GitHub at https://github.com/YudongGuo/AD-NeRF.