Blur appearance model that assumes that the input image was subject to blur.
More...
#include <esm.h>
|
|
template<typename PIXEL > |
| double | difference (const PIXEL &warped, const PIXEL &templatePixel) const |
| |
|
template<typename PIXEL > |
| std::pair< double, TooN::Vector< dimensions > > | difference_jacobian (const PIXEL &warped, const PIXEL &templatePixel) const |
| |
|
TooN::Vector< 2 > | image_jacobian (const TooN::Vector< 2 > &gradWarped, const TooN::Vector< 2 > &gradTemplate) const |
| |
|
void | update (const TooN::Vector< dimensions > &d) |
| |
|
|
static const int | dimensions = 0 |
| |
Blur appearance model that assumes that the input image was subject to blur.
There is no parameter to estimate, but the image jacobians look different.
- Todo:
- reference paper from Lepetit here
The documentation for this class was generated from the following file:
