search

graspnet / graspnet-baseline

Baseline model for "GraspNet-1Billion: A Large-Scale Benchmark for General Object Grasping" (CVPR 2020)
https://graspnet.net/
Other
415 stars 133 forks source link

A question about function `create_point_cloud_from_depth_image` #71

Closed elenacliu closed 10 months ago

elenacliu commented 11 months ago

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 commented 10 months ago

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