Metrically Scaled Depth Renders from Depth-Nerfacto

[geanrobotics]

After training depth-nerfacto on metrically scaled depth images (in millimetres) with corresponding aligned camera poses, I would like to be able to render out depth images that are represented in the same way i.e single-channel 16-bit depth image (in millimetres) instead of a colour map. Is there a way to achieve this?

[kerrj]

The outputs['depth'] from the model is a real float depth value, the viewer just converts it to a colormap. If you want the raw values you can save it in some other format like a numpy array