Open3D (C++ API)  0.18.0+252c867
Macros
RobustKernelImpl.h File Reference

(252c867 (Sun May 5 05:39:34 2024 +0000))

#include <cmath>
#include "open3d/core/CUDAUtils.h"
#include "open3d/t/geometry/kernel/GeometryMacros.h"
#include "open3d/t/pipelines/registration/RobustKernel.h"

Go to the source code of this file.

Macros

#define DISPATCH_ROBUST_KERNEL_FUNCTION(METHOD, scalar_t, scaling_parameter, shape_parameter, ...)
 
#define DISPATCH_DUAL_ROBUST_KERNEL_FUNCTION(scalar_t, METHOD_1, scaling_parameter_1, METHOD_2, scaling_parameter_2, ...)
 

Macro Definition Documentation

◆ DISPATCH_DUAL_ROBUST_KERNEL_FUNCTION

#define DISPATCH_DUAL_ROBUST_KERNEL_FUNCTION (   scalar_t,
  METHOD_1,
  scaling_parameter_1,
  METHOD_2,
  scaling_parameter_2,
  ... 
)
Parameters
scalar_ttype: float / double.
METHOD_1registration::RobustKernelMethod Loss type.
scaling_parameter_1Scaling parameter for loss fine-tuning.
METHOD_2registration::RobustKernelMethod Loss type.
scaling_parameter_2Scaling parameter for loss fine-tuning.

◆ DISPATCH_ROBUST_KERNEL_FUNCTION

#define DISPATCH_ROBUST_KERNEL_FUNCTION (   METHOD,
  scalar_t,
  scaling_parameter,
  shape_parameter,
  ... 
)

To use Robust Kernel functions please refer the unit-tests for t::registration or the implementation use cases at t::pipelines::kernel::ComputePosePointToPlaneCUDA and t::pipelines::kernel::ComputePosePointToPlaneCPU.

Parameters
METHODregistration::RobustKernelMethod Loss type.
scalar_ttype: float / double.
scaling_parameterScaling parameter for loss fine-tuning.
shape_parameterShape parameter for Generalized Loss method.