Matthew Tancik

The dataprocessing scales and rotates the data. The nerf coordinate frame can be determined using the dataparser_transform.json in the output folder. This can be used to get to the coordinate...

What version of python are you using?

Yep it can be run locally, the installation instructions are the same.

Unfortunately at this time the repo doesn't support this functionality. The way we currently handle distortions assumes all of the cameras are the same type so that it can be...

@brentyi had a response to this question on discord that is relavant here > I haven't worked on this part of the code, but my impression is that multiple camera...

This is great! Can you post example videos before and after. Also how are the videos saved when the resolution changes?

Hi, just checking in on this PR, looking forward to it being incorporated.

Use the `--rendered-output-names` argument, so for depth it is `--rendered-output-names depth` https://docs.nerf.studio/en/latest/reference/cli/ns_render.html For an accumulation mask use `accumulation` key. Not that in normal scenes trained in nerfacto there won't be...

The `vanilla-nerf` and `mipnerf` models are setup to work with the blender synthetic data, not real-world data. For real-world data, use `nerfacto` or `instant-ngp`

@kerrj Will this conflict with any of the datamanager stuff that you are working on?