A question about function `create_point_cloud_from_depth_image`

[elenacliu]

https://github.com/graspnet/graspnet-baseline/blob/46f649002bb8c7bb89bf0dfc1391aad3a919a1ea/utils/data_utils.py#L33-L43

In L38~L39, to get points' x, y coordinates in the camera space, why do you multiply points_z?

[chenxi-wang]

This is a basic transformation in point cloud computation. You can refer to related materials.