Closed wamiq-reyaz closed 1 year ago
Hi, wamiq-reyaz! The code dealing with DTU dataset is borrowed from neurecon and the processed DTU data is borrowed from Neus. You can refer to them for more details.
As far as I know, the camera coordinate is an opencv camera model (i.e. right: x-axis, down: y-axis).
The backbone of our method is Neus, which expects that the object is within a unit sphere (i.e. obj_bounding_radius
). Therefore the coordinate usually ranges from -1 to 1.
The white background is controlled by white_bkgd
in volume_render
.
Close the inactive issues. Feel free to reopen it if the problem still needs to be solved.
Hiya,
You guys have released code that deals with the DTU dataset. Could you please clarify the global coordinate frame and the camera coordinates that the code expects? This would be a great boon in training on our own datasets - especially the synthetic nerf dataset.
So the questions would be in the world coordinates is z-up? In the camera coordinates, what are the coordinate ranges after perspective transform (-1 to 1, or 0 to 1). In the camera, is +z the forward direction or is it -z?
Other question are:
object_bounding_radius
? it is set for nuemesh, but theget_neumesh_model
expects it under data?Hope you can answer. Cheers, Wamiq