![]() |
ACloudViewer
3.9.4
A Modern Library for 3D Data Processing
|
#include <Registration.h>

Public Member Functions | |
| RegistrationResult (const core::Tensor &transformation=core::Tensor::Eye(4, core::Float64, core::Device("CPU:0"))) | |
| Parameterized Constructor. More... | |
| ~RegistrationResult () | |
| bool | IsBetterThan (const RegistrationResult &other) const |
Public Attributes | |
| core::Tensor | transformation_ |
| The estimated transformation matrix of dtype Float64 on CPU device. More... | |
| core::Tensor | correspondences_ |
| double | inlier_rmse_ |
| RMSE of all inlier correspondences. Lower is better. More... | |
| double | fitness_ |
| bool | converged_ {false} |
| Specifies whether the algorithm converged or not. More... | |
| size_t | num_iterations_ {0} |
| Number of iterations the algorithm took to converge. More... | |
Class that contains the registration results.
Definition at line 65 of file Registration.h.
|
inline |
Parameterized Constructor.
| transformation | The estimated transformation matrix of dtype Float64 on CPU device. Default: Identity tensor. |
Definition at line 71 of file Registration.h.
|
inline |
Definition at line 75 of file Registration.h.
|
inline |
Definition at line 77 of file Registration.h.
References fitness_, and inlier_rmse_.
| bool cloudViewer::t::pipelines::registration::RegistrationResult::converged_ {false} |
Specifies whether the algorithm converged or not.
Definition at line 95 of file Registration.h.
Referenced by cloudViewer::t::pipelines::registration::pybind_registration_class().
| core::Tensor cloudViewer::t::pipelines::registration::RegistrationResult::correspondences_ |
Tensor containing indices of corresponding target points, where the value is the target index and the index of the value itself is the source index. It contains -1 as value at index with no correspondence.
Definition at line 88 of file Registration.h.
Referenced by cloudViewer::t::pipelines::registration::pybind_registration_class().
| double cloudViewer::t::pipelines::registration::RegistrationResult::fitness_ |
For ICP: the overlapping area (# of inlier correspondences / # of points in target). Higher is better.
Definition at line 93 of file Registration.h.
Referenced by cloudViewer::t::pipelines::registration::DoSingleScaleICPIterations(), IsBetterThan(), and cloudViewer::t::pipelines::registration::pybind_registration_class().
| double cloudViewer::t::pipelines::registration::RegistrationResult::inlier_rmse_ |
RMSE of all inlier correspondences. Lower is better.
Definition at line 90 of file Registration.h.
Referenced by cloudViewer::t::pipelines::registration::DoSingleScaleICPIterations(), IsBetterThan(), and cloudViewer::t::pipelines::registration::pybind_registration_class().
| size_t cloudViewer::t::pipelines::registration::RegistrationResult::num_iterations_ {0} |
Number of iterations the algorithm took to converge.
Definition at line 97 of file Registration.h.
Referenced by cloudViewer::t::pipelines::registration::pybind_registration_class().
| core::Tensor cloudViewer::t::pipelines::registration::RegistrationResult::transformation_ |
The estimated transformation matrix of dtype Float64 on CPU device.
Definition at line 84 of file Registration.h.
Referenced by cloudViewer::t::pipelines::registration::DoSingleScaleICPIterations(), and cloudViewer::t::pipelines::registration::pybind_registration_class().