I noticed that the camera distance is 1 in your image generation script. And in the 3D generation code, the camera distances are also normalized to 1. So, are the camera distances in training all set to 1, or they are between [0.9, 1.1] and only use 1 for generation?
They are normalized to 1 during training (the extrinsic becomes rotation only). Using the original extrinsic also works, but we just found it (normalized) simpler to use.
I noticed that the camera distance is 1 in your image generation script. And in the 3D generation code, the camera distances are also normalized to 1. So, are the camera distances in training all set to 1, or they are between [0.9, 1.1] and only use 1 for generation?