jadgardner / neusky Goto Github PK

Hello! Nice work! I would like to test the method using my own dataset. What steps should I follow to prepare the data in order to train NeuSky? Thank you!

we are planning to use your method as a baseline for a research project we are carrying out. Could you share approximate inference times using whichever GPUS you used?
As per equation 1, I understand that the required number of inferences per pixel is:
per sample in the ray:

• 1 inference to the sdf net to get the sigmas/alphas/weights for the alpha composition
• 1 inference to the albedo net to get the albedo color
• per direction (642 in total)
  • 1 inference of the reni++ network to obtain the hdr light coming from that direction
  • 1 inference to the ddf to obtain visibility
  • normal vector computed from the sdf
    Is there something I am missing?
    thanks very much in advance!

I am trying to build a docker image to run Neusky. To build this, I am using a nerfstudio docker base image but I haven't had any success in making it run with either 0.3.4, 1.0.0, or 1.0.1