Multi-thread MovingLeastSquares copy missing filed redundantly

Hi,

at mls.hpp performProcessing, it copy missing filed redundantly,
(So single thread version did not copy that at there...)

#ifdef _OPENMP
        computeMLSPointNormal (index, nn_indices, projected_points[tn], projected_points_normals[tn], corresponding_input_indices[tn], mls_results_[mls_result_index]);

        // Copy all information from the input cloud to the output points (not doing any interpolation)
        for (size_t pp = pp_size; pp < projected_points[tn].size (); ++pp)
          copyMissingFields (input_->points[(*indices_)[cp]], projected_points[tn][pp]);
#else
        computeMLSPointNormal (index, nn_indices, projected_points, projected_points_normals, *corresponding_input_indices_, mls_results_[mls_result_index]);

        // Append projected points to output
        output.insert (output.end (), projected_points.begin (), projected_points.end ());
        if (compute_normals_)
          normals_->insert (normals_->end (), projected_points_normals.begin (), projected_points_normals.end ());
#endif

because it is already copied at addProjectedPointNormal:

template <typename PointInT, typename PointOutT> void
pcl::MovingLeastSquares<PointInT, PointOutT>::addProjectedPointNormal (int index,
                                                                       const Eigen::Vector3d &point,
                                                                       const Eigen::Vector3d &normal,
                                                                       double curvature,
                                                                       PointCloudOut &projected_points,
                                                                       NormalCloud &projected_points_normals,
                                                                       PointIndices &corresponding_input_indices) const
{
  PointOutT aux;
  aux.x = static_cast<float> (point[0]);
  aux.y = static_cast<float> (point[1]);
  aux.z = static_cast<float> (point[2]);

  // Copy additional point information if available
  copyMissingFields (input_->points[index], aux);

  projected_points.push_back (aux);
  corresponding_input_indices.indices.push_back (index);

  if (compute_normals_)
  {
    pcl::Normal aux_normal;
    aux_normal.normal_x = static_cast<float> (normal[0]);
    aux_normal.normal_y = static_cast<float> (normal[1]);
    aux_normal.normal_z = static_cast<float> (normal[2]);
    aux_normal.curvature = curvature;
    projected_points_normals.push_back (aux_normal);
  }
}

Start in mls.hpp at performProcessing and addProjectedPointNormal, then compare the OpenMP and single-threaded paths. Confirm whether copyMissingFields is applied twice in the threaded path, and consider the issue complete when redundant copying is avoided without changing output fields in either path.