Matthew Tancik

Can you try pulling the latest github version and then post the error you are seeing.

Closing due to inactivity. Feel free to reopen if it is still and issue.

We intend to both keep updating nerfacto and add other models as they are released (for example there is currently a PR for adding NeRFPlayer). @akristoffersen has an implementation of...

A different solution is to pre-process/cache all of the data as rays at the beginning of training. We could then shuffle and then sample them like a more traditional ML...

Yea, thats where it gets more challenging. Not sure on the top of my head.

The models are typically trained for fewer iterations, ie nerfacto is only set to train for 30k iters. There are some instabilities that emerge when training for a long time....

My guess is that this is due to a change in PR #2350. This change was required for licensing reasons. @THE-COB could also chime in.

Nerfacto was designed to work well on real scenes (which in practice hurts performance on blender scenes). Take a look at #806 for some extra arguments for a better blender...

Yea, we really should have better benchmarking. Hopefully something we can improve going forward. One open challenge is how to properly evaluate methods on real data. Methods like nerfacto build...

It looks like the previous localtunnel call failed to create a localtunnel leading to an empty list. Can you try rerunning the notebook.