Matthew Tancik

The code should not use more than 16G of memory and should not have OOM errors for a single V100 GPU. We used V100s for the paper results. Is there...

You can use [this](https://github.com/bmild/nerf/files/4410324/360_view.py.zip) script as a starting point. You may need to make modifications for your specific blend file.

It looks like your GPU is running out of memory. The code config is for a v100 which as 16GB of memory. If you are running on a card with...

Ahh, it looks like your entire dataset doesn't fit on the GPU. Try adding `--no_batching`, this will load one image at a time during training. The results will be worse,...

Ok, if it is breaking when rendering the test example decrease the value for `--chunk`.

Yes, reducing `chunk` is preferred. It does not change to output of the training (unlike `N_samples` and `N_importance`), it just runs slower during the evaluations.

Try creating a `./logs\summaries` folder.

Oh, it looks like you are just trying to download the data. The script was made for linux so windows may be causing you issues. If you look at the...

The terminology is a little confusing. When no_batching is set to true, during each iteration the entire batch of rays are only sampled from a single image. When it is...

There are a few followup works that enable realtime rendering. Here are two with online demos, PlenOctrees - https://alexyu.net/plenoctrees/ SNeRG - https://phog.github.io/snerg/