Lex van der Sluijs

I have the same question. It would be great not to have to re-train every time the program is started. Am I overlooking something?

Update: I have found the solution: a checkpoint is actually automatically created, but you have to instruct the viewer to load it. This is described on this page: https://docs.nerf.studio/en/latest/quickstart/first_nerf.html ....

I am having the same issue. I can compute the Poster dataset with the --pipeline.model.predict-normals True, but then there is no rendering in the viewer. When I try to export...

That's a valid point, thanks. In the meantime -good news- I've gotten the code to work on Windows 10, using the Windows Linux Subsystem feature https://seanthegeek.net/234/graphical-linux-applications-bash-ubuntu-windows/. I wasn't able to...

Hi Chris, Is the script for training the model used in pc2cad.py in the repository? Then we could train the model ourselves. It would be very interesting to play with...

Great, thanks Chris!

Ah, thanks, that's good to know! Perhaps it's a good idea to add some text about this to the readme? If you want I can try to create a first...