open3d.ml.tf.ops.fixed_radius_search

open3d.ml.tf.ops.fixed_radius_search(points, queries, radius, points_row_splits, queries_row_splits, hash_table_splits, hash_table_index, hash_table_cell_splits, index_dtype=tf.int32, metric='L2', ignore_query_point=False, return_distances=False, name=None)

Computes the indices of all neighbors within a radius.

This op computes the neighborhood for each query point and returns the indices of the neighbors and optionally also the distances. The same fixed radius is used for each query point. Points and queries can be batched with each batch item having an individual number of points and queries. The following example shows a simple search with just a single batch item:

import open3d.ml.tf as ml3d

points = [
  [0.1,0.1,0.1],
  [0.5,0.5,0.5],
  [1.7,1.7,1.7],
  [1.8,1.8,1.8],
  [0.3,2.4,1.4]]

queries = [
    [1.0,1.0,1.0],
    [0.5,2.0,2.0],
    [0.5,2.1,2.1],
]

radius = 1.0

# build the spatial hash table for fixex_radius_search
table = ml3d.ops.build_spatial_hash_table(points,
                                          radius,
                                          points_row_splits=torch.LongTensor([0,5]),
                                          hash_table_size_factor=1/32)

# now run the fixed radius search
ml3d.ops.fixed_radius_search(points,
                             queries,
                             radius,
                             points_row_splits=torch.LongTensor([0,5]),
                             queries_row_splits=torch.LongTensor([0,3]),
                             **table._asdict())
# returns neighbors_index      = [1, 4, 4]
#         neighbors_row_splits = [0, 1, 2, 3]
#         neighbors_distance   = []

# or with pytorch
import torch
import open3d.ml.torch as ml3d

points = torch.Tensor([
  [0.1,0.1,0.1],
  [0.5,0.5,0.5],
  [1.7,1.7,1.7],
  [1.8,1.8,1.8],
  [0.3,2.4,1.4]])

queries = torch.Tensor([
    [1.0,1.0,1.0],
    [0.5,2.0,2.0],
    [0.5,2.1,2.1],
])

radius = 1.0

# build the spatial hash table for fixex_radius_search
table = ml3d.ops.build_spatial_hash_table(points,
                                          radius,
                                          points_row_splits=torch.LongTensor([0,5]),
                                          hash_table_size_factor=1/32)

# now run the fixed radius search
ml3d.ops.fixed_radius_search(points,
                             queries,
                             radius,
                             points_row_splits=torch.LongTensor([0,5]),
                             queries_row_splits=torch.LongTensor([0,3]),
                             **table._asdict())
# returns neighbors_index      = [1, 4, 4]
#         neighbors_row_splits = [0, 1, 2, 3]
#         neighbors_distance   = []

Parameters

• points –

  A Tensor. Must be one of the following types: float32, float64.

  The 3D positions of the input points.

• queries – A Tensor. Must have the same type as points. The 3D positions of the query points.

• radius – A Tensor. Must have the same type as points. A scalar with the neighborhood radius

• points_row_splits – A Tensor of type int64. 1D vector with the row splits information if points is batched. This vector is [0, num_points] if there is only 1 batch item.

• queries_row_splits – A Tensor of type int64. 1D vector with the row splits information if queries is batched. This vector is [0, num_queries] if there is only 1 batch item.

• hash_table_splits – A Tensor of type uint32. Array defining the start and end the hash table for each batch item. This is [0, number of cells] if there is only 1 batch item or [0, hash_table_cell_splits_size-1] which is the same.

• hash_table_index – A Tensor of type uint32. Stores the values of the hash table, which are the indices of the points. The start and end of each cell is defined by hash_table_cell_splits.

• hash_table_cell_splits – A Tensor of type uint32. Defines the start and end of each hash table cell.

• index_dtype –

  An optional tf.DType from: tf.int32, tf.int64. Defaults to tf.int32.

  The data type for the returned neighbor_index Tensor. Either int32 or int64. Default is int32.

• metric –

  An optional string from: “L1”, “L2”, “Linf”. Defaults to “L2”.

  Either L1, L2 or Linf. Default is L2

• ignore_query_point – An optional bool. Defaults to False. If true the points that coincide with the center of the search window will be ignored. This excludes the query point if ‘queries’ and ‘points’ are the same point cloud.

• return_distances – An optional bool. Defaults to False. If True the distances for each neighbor will be returned in the tensor ‘neighbors_distance’. If False a zero length Tensor will be returned for ‘neighbors_distance’.

• name – A name for the operation (optional).

Returns

A tuple of Tensor objects (neighbors_index, neighbors_row_splits, neighbors_distance).

neighbors_index: A Tensor of type index_dtype.

The compact list of indices of the neighbors. The corresponding query point can be inferred from the ‘neighbor_count_row_splits’ vector.

neighbors_row_splits: A Tensor of type int64.

The exclusive prefix sum of the neighbor count for the query points including the total neighbor count as the last element. The size of this array is the number of queries + 1.

neighbors_distance: A Tensor. Has the same type as points.

Stores the distance to each neighbor if ‘return_distances’ is True. Note that the distances are squared if metric is L2. This is a zero length Tensor if ‘return_distances’ is False.