Data Structures
class	FaissIndex
	Faiss for nearest neighbor search. More...

class	FixedRadiusIndex
	FixedRadiusIndex for nearest neighbor range search. More...

class	MemoryAllocation
	A class for managing memory segments within a memory allocation. More...

class	NanoFlannIndex

struct	NanoFlannIndexHolder
	NanoFlann Index Holder. More...

struct	NanoFlannIndexHolderBase
	Base struct for Index holder. More...

class	NearestNeighborSearch
	A Class for nearest neighbor search. More...

class	NeighborSearchAllocator

class	NNSIndex

Enumerations
enum	Metric { L1, L2, Linf, L1, L2, Linf }
	Distance metric enum. More...

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

Functions
template<class TReal , class TIndex >
void	BuildSpatialHashTableCUDA (void temp, size_t &temp_size, const size_t num_points, const TReal const points, const TReal radius, const size_t points_row_splits_size, const int64_t points_row_splits, const TIndex hash_table_splits, const size_t hash_table_cell_splits_size, TIndex hash_table_cell_splits, TIndex hash_table_index)

template<class T >
void	FixedRadiusSearchCUDA (void temp, size_t &temp_size, int64_t query_neighbors_row_splits, size_t num_points, const T const points, size_t num_queries, const T const queries, const T radius, const size_t points_row_splits_size, const int64_t const points_row_splits, const size_t queries_row_splits_size, const int64_t const queries_row_splits, const uint32_t const hash_table_splits, size_t hash_table_cell_splits_size, const uint32_t const hash_table_cell_splits, const uint32_t *const hash_table_index, NeighborSearchAllocator< T > &output_allocator)

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 [1/2]

enum open3d::core::nns::Metric

Supported metrics.

Enumerator
L1
L2
Linf
L1
L2
Linf

◆ Metric [2/2]

enum open3d::core::nns::Metric

Distance metric enum.

Enumerator
L1
L2
Linf
L1
L2
Linf

Function Documentation

◆ BuildSpatialHashTableCUDA()

template<class TReal , class TIndex >

void open3d::core::nns::BuildSpatialHashTableCUDA	(	void *	temp,
		size_t &	temp_size,
		const size_t	num_points,
		const TReal *const	points,
		const TReal	radius,
		const size_t	points_row_splits_size,
		const int64_t *	points_row_splits,
		const TIndex *	hash_table_splits,
		const size_t	hash_table_cell_splits_size,
		TIndex *	hash_table_cell_splits,
		TIndex *	hash_table_index
	)

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

All pointer arguments point to device memory unless stated otherwise.

Parameters

temp	Pointer to temporary memory. If nullptr then the required size of temporary memory will be written to `temp_size` and no work is done.
temp_size	The size of the temporary memory in bytes. This is used as an output if temp is nullptr
texture_alignment	The texture alignment in bytes. This is used for allocating segments within the temporary memory.
num_points	The number of points.
points	The array of 3D points.
radius	The radius that will be used for searching.
points_row_splits_size	The size of the points_row_splits array. The size of the array is batch_size+1.
points_row_splits	This pointer points to host memory. Defines the start and end of the points in each batch item. The size of the array is batch_size+1. If there is only 1 batch item then this array is [0, num_points]
hash_table_splits	This pointer points to host memory. 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_cell_splits_size	This is the length of the hash_table_cell_splits array.
hash_table_cell_splits	This is an output array 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.
hash_table_index	This is an output array storing the values of the hash table, which are the indices to the points. The size of the array must be equal to the number of points.

◆ 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

◆ FixedRadiusSearchCUDA()

template<class T >

void open3d::core::nns::FixedRadiusSearchCUDA	(	void *	temp,
		size_t &	temp_size,
		int64_t *	query_neighbors_row_splits,
		size_t	num_points,
		const T *const	points,
		size_t	num_queries,
		const T *const	queries,
		const T	radius,
		const size_t	points_row_splits_size,
		const int64_t *const	points_row_splits,
		const size_t	queries_row_splits_size,
		const int64_t *const	queries_row_splits,
		const uint32_t *const	hash_table_splits,
		size_t	hash_table_cell_splits_size,
		const uint32_t *const	hash_table_cell_splits,
		const uint32_t *const	hash_table_index,
		NeighborSearchAllocator< T > &	output_allocator
	)

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.

All pointer arguments point to device memory unless stated otherwise.

Template Parameters

T	Floating-point data type for the point positions.
OUTPUT_ALLOCATOR	Type of the output_allocator. See `output_allocator` for more information.

Parameters

temp	Pointer to temporary memory. If nullptr then the required size of temporary memory will be written to `temp_size` and no work is done.
temp_size	The size of the temporary memory in bytes. This is used as an output if temp is nullptr
texture_alignment	The texture alignment in bytes. This is used for allocating segments within the temporary memory.
query_neighbors_row_splits	This is the output pointer for the prefix sum. The length of this array is `num_queries` + 1.
num_points	The number of points.
points	Array with the 3D point positions. This may be the same array as `queries`.
num_queries	The number of query points.
queries	Array with the 3D query positions. This may be the same array as `points`.
radius	The search radius.
points_row_splits_size	The size of the points_row_splits array. The size of the array is batch_size+1.
points_row_splits	This pointer points to host memory. Defines the start and end of the points in each batch item. The size of the array is batch_size+1. If there is only 1 batch item then this array is [0, num_points]
queries_row_splits_size	The size of the queries_row_splits array. The size of the array is batch_size+1.
queries_row_splits	This pointer points to host memory. Defines the start and end of the queries in each batch item. The size of the array is batch_size+1. If there is only 1 batch item then this array is [0, num_queries]
hash_table_splits	This pointer points to host memory. 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_cell_splits_size	This is the length of the hash_table_cell_splits array.
hash_table_cell_splits	This is an output of the function BuildSpatialHashTableCUDA. The row splits array describing the start and end of each cell.
hash_table_index	This is an output of the function BuildSpatialHashTableCUDA. This is array storing the values of the hash table, which are the indices to the points. The size of the array must be equal to the number of points.
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!!
output_allocator	An object that implements functions for allocating the output arrays. The object must implement functions AllocIndices(int32_t ptr, size_t size) and AllocDistances(T ptr, size_t size). Both functions should allocate memory and return a pointer to that memory in ptr. Argument size specifies the size of the array as the number of elements. Both functions must accept the argument size==0. In this case ptr does not need to be set.

◆ SpatialHash() [1/2]

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

inline

Spatial hashing function for integer coordinates.

◆ SpatialHash() [2/2]

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

inline

Data Structures

Enumerations

Functions

Enumeration Type Documentation

◆ Metric [1/2]

◆ Metric [2/2]

Function Documentation

◆ BuildSpatialHashTableCUDA()

◆ ComputeVoxelIndex()

◆ FixedRadiusSearchCUDA()

◆ SpatialHash() [1/2]

◆ SpatialHash() [2/2]