Sparse match interpolation algorithm based on modified piecewise locally-weighted affine estimator called Robust Interpolation method of Correspondences or RIC from [117] and Variational and Fast Global Smoother as post-processing filter. The RICInterpolator is a extension of the EdgeAwareInterpolator. Main concept of this extension is an piece-wise affine model based on over-segmentation via SLIC superpixel estimation. The method contains an efficient propagation mechanism to estimate among the pieces-wise models.
More...
|
virtual float | getAlpha () const =0 |
| Alpha is a parameter defining a global weight for transforming geodesic distance into weight. More...
|
|
virtual float | getFGSLambda () const =0 |
| Sets the respective fastGlobalSmootherFilter() parameter. More...
|
|
virtual float | getFGSSigma () const =0 |
| Sets the respective fastGlobalSmootherFilter() parameter. More...
|
|
virtual int | getK () const =0 |
| K is a number of nearest-neighbor matches considered, when fitting a locally affine model for a superpixel segment. However, lower values would make the interpolation noticeably faster. The original implementation of [117] uses 32. More...
|
|
virtual float | getMaxFlow () const =0 |
| MaxFlow is a threshold to validate the predictions using a certain piece-wise affine model. If the prediction exceeds the treshold the translational model will be applied instead. More...
|
|
virtual int | getModelIter () const =0 |
| Parameter defining the number of iterations for piece-wise affine model estimation. More...
|
|
virtual bool | getRefineModels () const =0 |
| Parameter to choose wether additional refinement of the piece-wise affine models is employed. More...
|
|
virtual int | getSuperpixelMode () const =0 |
| Parameter to choose superpixel algorithm variant to use: More...
|
|
virtual int | getSuperpixelNNCnt () const =0 |
| Parameter defines the number of nearest-neighbor matches for each superpixel considered, when fitting a locally affine model. More...
|
|
virtual float | getSuperpixelRuler () const =0 |
| Parameter to tune enforcement of superpixel smoothness factor used for oversegmentation. More...
|
|
virtual int | getSuperpixelSize () const =0 |
| Get the internal cost, i.e. edge map, used for estimating the edge-aware term. More...
|
|
virtual bool | getUseGlobalSmootherFilter () const =0 |
| Sets whether the fastGlobalSmootherFilter() post-processing is employed. More...
|
|
virtual bool | getUseVariationalRefinement () const =0 |
| Parameter to choose wether the VariationalRefinement post-processing is employed. More...
|
|
virtual void | setAlpha (float alpha=0.7f)=0 |
| Alpha is a parameter defining a global weight for transforming geodesic distance into weight. More...
|
|
virtual void | setCostMap (const Mat &costMap)=0 |
| Interface to provide a more elaborated cost map, i.e. edge map, for the edge-aware term. This implementation is based on a rather simple gradient-based edge map estimation. To used more complex edge map estimator (e.g. StructuredEdgeDetection that has been used in the original publication) that may lead to improved accuracies, the internal edge map estimation can be bypassed here. More...
|
|
virtual void | setFGSLambda (float lambda=500.f)=0 |
| Sets the respective fastGlobalSmootherFilter() parameter. More...
|
|
virtual void | setFGSSigma (float sigma=1.5f)=0 |
| Sets the respective fastGlobalSmootherFilter() parameter. More...
|
|
virtual void | setK (int k=32)=0 |
| K is a number of nearest-neighbor matches considered, when fitting a locally affine model for a superpixel segment. However, lower values would make the interpolation noticeably faster. The original implementation of [117] uses 32. More...
|
|
virtual void | setMaxFlow (float maxFlow=250.f)=0 |
| MaxFlow is a threshold to validate the predictions using a certain piece-wise affine model. If the prediction exceeds the treshold the translational model will be applied instead. More...
|
|
virtual void | setModelIter (int modelIter=4)=0 |
| Parameter defining the number of iterations for piece-wise affine model estimation. More...
|
|
virtual void | setRefineModels (bool refineModles=true)=0 |
| Parameter to choose wether additional refinement of the piece-wise affine models is employed. More...
|
|
virtual void | setSuperpixelMode (int mode=100)=0 |
| Parameter to choose superpixel algorithm variant to use: More...
|
|
virtual void | setSuperpixelNNCnt (int spNN=150)=0 |
| Parameter defines the number of nearest-neighbor matches for each superpixel considered, when fitting a locally affine model. More...
|
|
virtual void | setSuperpixelRuler (float ruler=15.f)=0 |
| Parameter to tune enforcement of superpixel smoothness factor used for oversegmentation. More...
|
|
virtual void | setSuperpixelSize (int spSize=15)=0 |
| Get the internal cost, i.e. edge map, used for estimating the edge-aware term. More...
|
|
virtual void | setUseGlobalSmootherFilter (bool use_FGS=true)=0 |
| Sets whether the fastGlobalSmootherFilter() post-processing is employed. More...
|
|
virtual void | setUseVariationalRefinement (bool use_variational_refinement=false)=0 |
| Parameter to choose wether the VariationalRefinement post-processing is employed. More...
|
|
virtual void | interpolate (InputArray from_image, InputArray from_points, InputArray to_image, InputArray to_points, OutputArray dense_flow)=0 |
| Interpolate input sparse matches. More...
|
|
| Algorithm () |
|
virtual | ~Algorithm () |
|
virtual void | clear () |
| Clears the algorithm state. More...
|
|
virtual bool | empty () const |
| Returns true if the Algorithm is empty (e.g. in the very beginning or after unsuccessful read. More...
|
|
virtual String | getDefaultName () const |
|
virtual void | read (const FileNode &fn) |
| Reads algorithm parameters from a file storage. More...
|
|
virtual void | save (const String &filename) const |
|
virtual void | write (FileStorage &fs) const |
| Stores algorithm parameters in a file storage. More...
|
|
void | write (const Ptr< FileStorage > &fs, const String &name=String()) const |
| simplified API for language bindings This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts. More...
|
|
Sparse match interpolation algorithm based on modified piecewise locally-weighted affine estimator called Robust Interpolation method of Correspondences or RIC from [117] and Variational and Fast Global Smoother as post-processing filter. The RICInterpolator is a extension of the EdgeAwareInterpolator. Main concept of this extension is an piece-wise affine model based on over-segmentation via SLIC superpixel estimation. The method contains an efficient propagation mechanism to estimate among the pieces-wise models.