Training for a video with static background

apple / ml-neuman

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

Other

1.26k stars 141 forks source link

Training for a video with static background #73

Open shngt opened 1 year ago

shngt commented 1 year ago

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!

jiangwei221 commented 1 year ago

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