|
| NGFParams (const AMParams *am_params, double _eta, bool _use_ssd) |
| value constructor
|
|
| NGFParams (const NGFParams *params=nullptr) |
| default/copy constructor
|
|
| AMParams (int _resx, int _resy, double _grad_eps=GRAD_EPS, double _hess_eps=HESS_EPS, bool _uchar_input=UCHAR_INPUT, double _likelihood_alpha=AM_LIKELIHOOD_ALPHA, double _likelihood_beta=AM_LIKELIHOOD_BETA, bool _dist_from_likelihood=AM_DIST_FROM_LIKELIHOOD, double _learning_rate=AM_LEARNING_RATE, IlluminationModel *_ilm=nullptr) |
|
| AMParams (const AMParams *am_params=nullptr) |
|
| ImgParams (int _resx, int _resy, double _grad_eps=GRAD_EPS, double _hess_eps=HESS_EPS, bool _uchar_input=UCHAR_INPUT) |
|
| ImgParams (const ImgParams *img_params=nullptr) |
|
|
double | eta |
| estimate of noise level in the image
|
|
bool | use_ssd |
| use SSD formulation of NGF (not implemented completely yet);
|
|
double | likelihood_alpha |
| multiplicative and additive factors for the exponent in the likelihood
|
|
double | likelihood_beta |
|
bool | dist_from_likelihood |
| use negative of likelihood as the distance measure
|
|
double | learning_rate |
| optional factor to control the rate of online learning
|
|
ILM | ilm |
| optional parametric function of pixel values that can account for lighting changes
|
|
int | resx |
| horizontal and vertical sampling resolutions
|
|
int | resy |
|
double | grad_eps |
| numerical increment/decrement used for computing image hessian and gradient using the method of finite differences
|
|
double | hess_eps |
|
bool | uchar_input |
|
The documentation for this struct was generated from the following file: