open3d::core::nns Namespace Reference

Namespaces
	impl

Data Structures
class	FixedRadiusIndex
	FixedRadiusIndex for nearest neighbor range search. More...
class	KnnIndex
class	MemoryAllocation
	A class for managing memory segments within a memory allocation. More...
struct	NanoFlannIndexHolder
	NanoFlann Index Holder. More...
class	NanoFlannIndex
class	NearestNeighborSearch
	A Class for nearest neighbor search. More...
class	NeighborSearchAllocator
struct	NanoFlannIndexHolderBase
	Base struct for NanoFlann index holder. More...
class	NNSIndex

Enumerations
enum	Metric { L1 , L2 , Linf }
	Supported metrics. More...

Functions
template<class T >
void	BuildSpatialHashTableCPU (const Tensor &points, double radius, const Tensor &points_row_splits, const Tensor &hash_table_splits, Tensor &hash_table_index, Tensor &hash_table_cell_splits)
template<class T , class TIndex >
void	FixedRadiusSearchCPU (const Tensor &points, const Tensor &queries, double radius, const Tensor &points_row_splits, const Tensor &queries_row_splits, const Tensor &hash_table_splits, const Tensor &hash_table_index, const Tensor &hash_table_cell_splits, const Metric metric, const bool ignore_query_point, const bool return_distances, const bool sort, Tensor &neighbors_index, Tensor &neighbors_row_splits, Tensor &neighbors_distance)
template<class T , class TIndex >
void	HybridSearchCPU (const Tensor &points, const Tensor &queries, double radius, int max_knn, const Tensor &points_row_splits, const Tensor &queries_row_splits, const Tensor &hash_table_splits, const Tensor &hash_table_index, const Tensor &hash_table_cell_splits, const Metric metric, Tensor &neighbors_index, Tensor &neighbors_count, Tensor &neighbors_distance)
HOST_DEVICE size_t	SpatialHash (int x, int y, int z)
	Spatial hashing function for integer coordinates. More...
HOST_DEVICE size_t	SpatialHash (const utility::MiniVec< int, 3 > &xyz)
template<class TVecf >
HOST_DEVICE utility::MiniVec< int, 3 >	ComputeVoxelIndex (const TVecf &pos, const typename TVecf::Scalar_t &inv_voxel_size)

Enumeration Type Documentation

Metric

enum open3d::core::nns::Metric

Supported metrics.

Enumerator
L1
L2
Linf

Function Documentation

BuildSpatialHashTableCPU()

template<class T >

void open3d::core::nns::BuildSpatialHashTableCPU	(	const Tensor &	points,
		double	radius,
		const Tensor &	points_row_splits,
		const Tensor &	hash_table_splits,
		Tensor &	hash_table_index,
		Tensor &	hash_table_cell_splits
	)

Builds a spatial hash table for a fixed radius search of 3D points.

Template Parameters

T	Floating-point data type for the point positions.

Parameters

points	The tensor of 3D points. This tensor may be splitted into multiple batch items by defining points_row_splits_size accordingly.
radius	The radius that will be used for searching.
points_row_splits	Defines the start and end of the points in each batch item. The size of the tensor is batch_size+1. If there is only 1 batch item then this array is [0, num_points]
hash_table_splits	Tensor 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	This is an output tensor storing the values of the hash table, which are the indices to the points. The size of the tensor must be equal to the number of points.
hash_table_cell_splits	This is an output tensor storing the start of each hash table entry. The size of this array defines the size of the hash table. The hash table size is hash_table_cell_splits_size - 1.

ComputeVoxelIndex()

template<class TVecf >

HOST_DEVICE utility::MiniVec<int, 3> open3d::core::nns::ComputeVoxelIndex ( const TVecf &  pos, const typename TVecf::Scalar_t &  inv_voxel_size  )

inline

Computes an integer voxel index for a 3D position.

Parameters

pos	A 3D position.
inv_voxel_size	The reciprocal of the voxel size

FixedRadiusSearchCPU()

template<class T , class TIndex >

void open3d::core::nns::FixedRadiusSearchCPU	(	const Tensor &	points,
		const Tensor &	queries,
		double	radius,
		const Tensor &	points_row_splits,
		const Tensor &	queries_row_splits,
		const Tensor &	hash_table_splits,
		const Tensor &	hash_table_index,
		const Tensor &	hash_table_cell_splits,
		const Metric	metric,
		const bool	ignore_query_point,
		const bool	return_distances,
		const bool	sort,
		Tensor &	neighbors_index,
		Tensor &	neighbors_row_splits,
		Tensor &	neighbors_distance
	)

Fixed radius search. This function computes a list of neighbor indices for each query point. The lists are stored linearly and an exclusive prefix sum defines the start and end of list in the array. In addition the function optionally can return the distances for each neighbor in the same format as the indices to the neighbors.

Template Parameters

T	Floating-point data type for the point positions.

Parameters

points	Tensor with the 3D point positions. This must be the tensor that was used for building the spatial hash table.
queries	Tensor with the 3D query positions. This may be the same tensor as points.
radius	The search radius.
points_row_splits	Defines the start and end of the points in each batch item. The size of the tensor is batch_size+1. If there is only 1 batch item then this tensor is [0, num_points]
queries_row_splits	Defines the start and end of the queries in each batch item. The size of the tensor is batch_size+1. If there is only 1 batch item then this tensor is [0, num_queries]
hash_table_splits	Tensor 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	This is an output of the function BuildSpatialHashTableCPU. This is tensor storing the values of the hash table, which are the indices to the points. The size of the tensor must be equal to the number of points.
hash_table_cell_splits	This is an output of the function BuildSpatialHashTableCPU. The row splits array describing the start and end of each cell.
metric	One of L1, L2, Linf. Defines the distance metric for the search.
ignore_query_point	If true then points with the same position as the query point will be ignored.
return_distances	If true then this function will return the distances for each neighbor to its query point in the same format as the indices. Note that for the L2 metric the squared distances will be returned!!
sort	If true then sort the results in ascending order of distance
neighbors_index	The output tensor that saves the resulting neighbor indices
neighbors_row_splits	Tensor defining the start and end the neighbor indices in each batch item. The size of the tensor is num_query_points + 1
neighbors_distance	The output tensor that saves the resulting neighbor distances.

HybridSearchCPU()

template<class T , class TIndex >

void open3d::core::nns::HybridSearchCPU	(	const Tensor &	points,
		const Tensor &	queries,
		double	radius,
		int	max_knn,
		const Tensor &	points_row_splits,
		const Tensor &	queries_row_splits,
		const Tensor &	hash_table_splits,
		const Tensor &	hash_table_index,
		const Tensor &	hash_table_cell_splits,
		const Metric	metric,
		Tensor &	neighbors_index,
		Tensor &	neighbors_count,
		Tensor &	neighbors_distance
	)

Hybrid search. This function computes a list of neighbor indices for each query point. The lists are stored linearly and if there is less neighbors than requested, the output tensor will be assigned with default values, -1 for indices and 0 for distances. In addition the function returns the number of neighbors for each query.

Template Parameters

T	Floating-point data type for the point positions.

Parameters

points	Tensor with the 3D point positions. This must be the tensor that was used for building the spatial hash table.
queries	Tensor with the 3D query positions. This may be the same tensor as points.
radius	The search radius.
max_knn	The maximum number of neighbor for each query
points_row_splits	Defines the start and end of the points in each batch item. The size of the tensor is batch_size+1. If there is only 1 batch item then this tensor is [0, num_points]
queries_row_splits	Defines the start and end of the queries in each batch item. The size of the tensor is batch_size+1. If there is only 1 batch item then this tensor is [0, num_queries]
hash_table_splits	Tensor 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	This is an output of the function BuildSpatialHashTableCPU. This is tensor storing the values of the hash table, which are the indices to the points. The size of the tensor must be equal to the number of points.
hash_table_cell_splits	This is an output of the function BuildSpatialHashTableCPU. The row splits array describing the start and end of each cell.
metric	One of L1, L2, Linf. Defines the distance metric for the search.
neighbors_index	The output tensor that saves the resulting neighbor indices
neighbors_count	The output tensor that saves the number of neighbors for each query points
neighbors_distance	The output tensor that saves the resulting neighbor distances.

SpatialHash() [1/2]

HOST_DEVICE size_t open3d::core::nns::SpatialHash ( const utility::MiniVec< int, 3 > &  xyz )

inline

SpatialHash() [2/2]

HOST_DEVICE size_t open3d::core::nns::SpatialHash ( int  x, int  y, int  z  )

inline

Spatial hashing function for integer coordinates.