Open buaacyw opened 1 year ago
Hi,
Thanks. I understand! I think we only need to fix the background rays. The near and far of human rays are correct. Since they are calculated in this way: https://github.com/apple/ml-neuman/blob/84d4685074327227457276f1b60d467f3dab1211/utils/ray_utils.py#L204-L219
The z0
is the distance with the principal point.
I found most of the NeRF works haven't taken this into consideration (including the origin NeRF). But they can still get a well-looking depth map.
Hi, thanks for your work! I have below questions about near-far computation in NeuMan:
pts = rays_o + rays_d * z_vals
, in whichrays_d
is normalized directions andz_vals
are sampled betweennear
andfar
. Thenear
andfar
are depth (vertical distance with the image plane, but not distance with the principal point). But if points are sampled bypts = rays_o + rays_d * z_vals
, the vertical distance between these points and the image plane is not fromnear
andfar
. Why is this? Is this wrong?Thanks!