search

YudongGuo / AD-NeRF

This repository contains a PyTorch implementation of "AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesis".
MIT License
1.03k stars 173 forks source link

Head and Torso mismatch while rendering. #105

Open Joshi21787 opened 2 years ago

Joshi21787 commented 2 years ago

Hello Sir,

I am trying to generated the results with pre-trained models and config file given at:

https://github.com/YudongGuo/AD-NeRF/tree/master/pretrained_models

But while rendering, final outcome has mismatch between head and torso a shown below.

https://user-images.githubusercontent.com/40563039/187200071-c87cfd02-3233-4ae0-a2a2-32f6d2529b19.mp4

Can you please help me what kind of parameter tuning is required to get the proper results.

Thank you.

ZziTaiLeo commented 2 years ago

I have the same question! Should I need to fine tuning two Nerfs?

piwawa commented 9 months ago

Hello Sir,

I am trying to generated the results with pre-trained models and config file given at:

https://github.com/YudongGuo/AD-NeRF/tree/master/pretrained_models

But while rendering, final outcome has mismatch between head and torso a shown below.

OUTPUT.mp4 Can you please help me what kind of parameter tuning is required to get the proper results.

Thank you.

我跑完咋没看到保存的结果？在哪个目录？怎么设置输出路径？