kaolin.ops.pointcloud.center_points(points, normalize=False, eps=1e-06)

Returns points centered at the origin for every pointcloud. If normalize is set, will also normalize each point cloud spearately to the range of [-0.5, 0.5]. Note that each point cloud is centered individually.

  • points (torch.FloatTensor) – point clouds of shape \((\text{batch_size}, \text{num_points}, 3)\), (other channel numbers supported).

  • normalize (bool) – if true, will also normalize each point cloud to be in the range [-0.5, 0.5]

  • eps (float) – eps to use to avoid division by zero when normalizing


(torch.FloatTensor) modified points with same shape, device and dtype as input