open3d::t::pipelines::registration Namespace Reference

Data Structures
class	ICPConvergenceCriteria
	Class that defines the convergence criteria of ICP. More...
class	RegistrationResult
class	TransformationEstimation
class	TransformationEstimationPointToPlane
class	TransformationEstimationPointToPoint

Typedefs
typedef std::pair< core::Tensor, core::Tensor >	CorrespondenceSet
	CorrespondenceSet: pair of 2x Int64 tensors of shape {C,}, where C is the number of good correspondences between source and target pointcloud. The first tensor is the source indices, and the second tensor is corresponding target indices. Such that, source[correspondence.first] and target[correspondence.second] is a correspondence pair. More...

Enumerations
enum	TransformationEstimationType { TransformationEstimationType::Unspecified = 0, TransformationEstimationType::PointToPoint = 1, TransformationEstimationType::PointToPlane = 2, TransformationEstimationType::ColoredICP = 3 }

Functions
RegistrationResult	EvaluateRegistration (const geometry::PointCloud &source, const geometry::PointCloud &target, double max_correspondence_distance, const core::Tensor &transformation=core::Tensor::Eye( 4, core::Dtype::Float64, core::Device("CPU:0")))
	Function for evaluating registration between point clouds. More...
RegistrationResult	RegistrationICP (const geometry::PointCloud &source, const geometry::PointCloud &target, double max_correspondence_distance, const core::Tensor &init_source_to_target=core::Tensor::Eye( 4, core::Dtype::Float64, core::Device("CPU:0")), const TransformationEstimation &estimation=TransformationEstimationPointToPoint(), const ICPConvergenceCriteria &criteria=ICPConvergenceCriteria())
	Functions for ICP registration. More...
RegistrationResult	RegistrationMultiScaleICP (const geometry::PointCloud &source, const geometry::PointCloud &target, const std::vector< double > &voxel_sizes, const std::vector< ICPConvergenceCriteria > &criteria_list, const std::vector< double > &max_correspondence_distances, const core::Tensor &init_source_to_target=core::Tensor::Eye( 4, core::Dtype::Float64, core::Device("CPU:0")), const TransformationEstimation &estimation=TransformationEstimationPointToPoint())
	Functions for Multi-Scale ICP registration. It will run ICP on different voxel level, from coarse to dense. The vector of ICPConvergenceCriteria(relative fitness, relative rmse, max_iterations) contains the stoping condition for each voxel level. The length of voxel_sizes vector, criteria vector, max_correspondence_distances vector must be same, and voxel_sizes must contain positive values in strictly decreasing order [Lower the voxel size, higher is the resolution]. Only the last value of the voxel_sizes vector can be {-1}, as it allows to run on the original scale without downsampling. More...

Typedef Documentation

CorrespondenceSet

typedef std::pair<core::Tensor, core::Tensor> open3d::t::pipelines::registration::CorrespondenceSet

CorrespondenceSet: pair of 2x Int64 tensors of shape {C,}, where C is the number of good correspondences between source and target pointcloud. The first tensor is the source indices, and the second tensor is corresponding target indices. Such that, source[correspondence.first] and target[correspondence.second] is a correspondence pair.

Enumeration Type Documentation

TransformationEstimationType

enum open3d::t::pipelines::registration::TransformationEstimationType

strong

Enumerator
Unspecified
PointToPoint
PointToPlane
ColoredICP

Function Documentation

EvaluateRegistration()

RegistrationResult open3d::t::pipelines::registration::EvaluateRegistration	(	const geometry::PointCloud &	source,
		const geometry::PointCloud &	target,
		double	max_correspondence_distance,
		const core::Tensor &	transformation = core::Tensor::Eye( 4, core::Dtype::Float64, core::Device("CPU:0"))
	)

Function for evaluating registration between point clouds.

Parameters

source	The source point cloud.
target	The target point cloud.
max_correspondence_distance	Maximum correspondence points-pair distance.
transformation	The 4x4 transformation matrix to transform source to target of dtype Float64 on CPU device.

RegistrationICP()

RegistrationResult open3d::t::pipelines::registration::RegistrationICP	(	const geometry::PointCloud &	source,
		const geometry::PointCloud &	target,
		double	max_correspondence_distance,
		const core::Tensor &	init_source_to_target = core::Tensor::Eye( 4, core::Dtype::Float64, core::Device("CPU:0")),
		const TransformationEstimation &	estimation = TransformationEstimationPointToPoint(),
		const ICPConvergenceCriteria &	criteria = ICPConvergenceCriteria()
	)

Functions for ICP registration.

Parameters

source	The source point cloud.
target	The target point cloud.
max_correspondence_distance	Maximum correspondence points-pair distance.
init_source_to_target	Initial transformation estimation of type Float64 on CPU.
estimation	Estimation method.
criteria	Convergence criteria.

RegistrationMultiScaleICP()

RegistrationResult open3d::t::pipelines::registration::RegistrationMultiScaleICP	(	const geometry::PointCloud &	source,
		const geometry::PointCloud &	target,
		const std::vector< double > &	voxel_sizes,
		const std::vector< ICPConvergenceCriteria > &	criteria_list,
		const std::vector< double > &	max_correspondence_distances,
		const core::Tensor &	init_source_to_target = core::Tensor::Eye( 4, core::Dtype::Float64, core::Device("CPU:0")),
		const TransformationEstimation &	estimation = TransformationEstimationPointToPoint()
	)

Functions for Multi-Scale ICP registration. It will run ICP on different voxel level, from coarse to dense. The vector of ICPConvergenceCriteria(relative fitness, relative rmse, max_iterations) contains the stoping condition for each voxel level. The length of voxel_sizes vector, criteria vector, max_correspondence_distances vector must be same, and voxel_sizes must contain positive values in strictly decreasing order [Lower the voxel size, higher is the resolution]. Only the last value of the voxel_sizes vector can be {-1}, as it allows to run on the original scale without downsampling.

Parameters

source	The source point cloud.
target	The target point cloud.
voxel_sizes	VectorDouble of voxel scales of type double.
criteria_list	Vector of ICPConvergenceCriteria objects for each scale.
max_correspondence_distances	VectorDouble of maximum correspondence points-pair distances of type double, for each iteration. Must be of same length as voxel_sizes and criterias.
init_source_to_target	Initial transformation estimation of type Float64 on CPU.
estimation	Estimation method.