concepts.vision.george_vision_pipeline.object_centric_vision.get_pointcloud_multicam#

get_pointcloud_multicam(color_images, depth_images, camera_transformations)[source]#

Reconstruct a colored point cloud from a color and depth image.

Parameters:
  • color_images (ndarray) – a numpy array of shape (N, H, W, 3) representing the color image.

  • depth_images (ndarray) – a numpy array of shape (N, H, W) representing the depth image.

  • camera_transformations (List[CameraTransformation]) – N CameraTransformation object.

Returns:

a colored open3d point cloud.

Return type:

open3d.geometry.PointCloud