search

NVIDIAGameWorks / kaolin-wisp

NVIDIA Kaolin Wisp is a PyTorch library powered by NVIDIA Kaolin Core to work with neural fields (including NeRFs, NGLOD, instant-ngp and VQAD).
Other
1.45k stars 133 forks source link

Config parser does not support FunnyNeuralField when running the latent nerf example #88

Closed royorel closed 1 year ago

royorel commented 1 year ago

Great work on this library!!

One issue I encountered is that the config parser does not support the FunnyNeuralField class in the latent nerf example. It raises a value error and the example can't run. Simply adding FunnyNeural Field to the parser won't work since it has no init function and the base_nef init function won't initialize it properly.

https://github.com/NVIDIAGameWorks/kaolin-wisp/blob/d118afd8bc40557e75754aa2e587c1a0d3ec8fd2/wisp/config_parser.py#L586-L614

orperel commented 1 year ago

Hi @royorel ! Thanks for reporting this one! We have a new version that fixes that and revises the demo which should be up very soon

orperel commented 1 year ago

@royorel Should be fixed now with #91

We also simplified the demo a bit to make it more "beginner friendly", but the hard-coded settings also reduce the output quality a bit (for the time being).