A question about function `create_point_cloud_from_depth_image`

[elenacliu]

graspnet-baseline/utils/data_utils.py

Lines 33 to 43 in 46f6490

	assert(depth.shape[0] == camera.height and depth.shape[1] == camera.width)
	xmap = np.arange(camera.width)
	ymap = np.arange(camera.height)
	xmap, ymap = np.meshgrid(xmap, ymap)
	points_z = depth / camera.scale
	points_x = (xmap - camera.cx) * points_z / camera.fx
	points_y = (ymap - camera.cy) * points_z / camera.fy
	cloud = np.stack([points_x, points_y, points_z], axis=-1)
	if not organized:
	cloud = cloud.reshape([-1, 3])
	return cloud

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.