Problem related to normalize_z setting

[vdvchen]

Hi, thanks for the great work.

While reading the code I find the normalize_z setting a bit confusing.

In https://github.com/sxyu/pixel-nerf/blob/a5a514224272a91e3ec590f215567032e1f1c260/src/model/models.py#L171, you neglect the translation for camera pose while encoding view space position. I'm wondering what is the rationale behind this processing.