apple / ml-neuman

Official repository of NeuMan: Neural Human Radiance Field from a Single Video (ECCV 2022)

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Training for a video with static background

shngt opened this issue · comments

It seems that the preprocessing fails for custom videos with a static background because colmap is unable to perform scene reconstruction. (ERROR: failed to create sparse model) Do you have any tips for handling videos like this?

Thank you very much for this project!

No, our preprocessing system and our background NeRF can't handle such videos.