Grangeat-based 2D/3D image registration
Loading...
Searching...
No Matches
Classes | Namespaces | Functions
ProjectDRR.h File Reference

Implementations of DRR projection functions. More...

#include "Common.h"

Go to the source code of this file.

Classes

struct  reg23::ProjectDRR< texture_t >
 
struct  reg23::ProjectDRR< texture_t >::CommonData
 

Namespaces

namespace  reg23
 

Functions

at::Tensor reg23::ProjectDRR_CPU (const at::Tensor &volume, const at::Tensor &voxelSpacing, const at::Tensor &homographyMatrixInverse, double sourceDistance, int64_t outputWidth, int64_t outputHeight, const at::Tensor &outputOffset, const at::Tensor &detectorSpacing)
 Generate a DRR from the given volume at the given transformation.
 
__host__ at::Tensor reg23::ProjectDRR_CUDA (const at::Tensor &volume, const at::Tensor &voxelSpacing, const at::Tensor &homographyMatrixInverse, double sourceDistance, int64_t outputWidth, int64_t outputHeight, const at::Tensor &outputOffset, const at::Tensor &detectorSpacing)
 An implementation of reg23::ProjectDRR_CPU that uses CUDA parallelisation.
 
at::Tensor reg23::ProjectDRR_backward_CPU (const at::Tensor &volume, const at::Tensor &voxelSpacing, const at::Tensor &homographyMatrixInverse, double sourceDistance, int64_t outputWidth, int64_t outputHeight, const at::Tensor &outputOffset, const at::Tensor &detectorSpacing, const at::Tensor &dLossDDRR)
 Evaluate the derivative of some scalar loss that is a function of a DRR projected from the given volume at the given transformation, with respect to the inverse homography matrix.
 
__host__ at::Tensor reg23::ProjectDRR_backward_CUDA (const at::Tensor &volume, const at::Tensor &voxelSpacing, const at::Tensor &homographyMatrixInverse, double sourceDistance, int64_t outputWidth, int64_t outputHeight, const at::Tensor &outputOffset, const at::Tensor &detectorSpacing, const at::Tensor &dLossDDRR)
 An implementation of reg23::ProjectDRR_backward_CPU that uses CUDA parallelisation.
 
__host__ at::Tensor reg23::ProjectDRRsBatched_CUDA (const at::Tensor &volume, const at::Tensor &voxelSpacing, const at::Tensor &invHMatrices, double sourceDistance, int64_t outputWidth, int64_t outputHeight, const at::Tensor &outputOffset, const at::Tensor &detectorSpacing)
 An implementation similar to reg23::ProjectDRR_CUDA that evaluates projections for multiple transformations in parallel.
 

Detailed Description

Implementations of DRR projection functions.