How to train the model using my own data?

[jinjiujiujin]

Hello! Thank you for sharing the code.
I have a video recorded in a real-life scenario and have utilized COLMAP to calculate the camera parameters. However, I have trouble in getting the light position and light intensity. Would you kindly guide me on how to obtain them? Thank you very much!

[iamNCJ]

Hi! Thank you for your interest in our work.
You might need to refer to Chap. 3.4 Data Acquisition in our paper for data capturing process. Basically, you need to capture with 2 devices at the same time, and the second camera needs to turn on its colocated flashlight. The position of the second camera is then used as the light position. There should be no other major sources of incident lighting during capturing.
As for light intensity, we are not using them in our model, so the only thing you need to make sure of is to lock the exposure on your camera (as all NeRF capturing requires, and also don't change the brightness of your second camera's flashlight) and fill in a constant number to this field in your data.