Super Resolution

Overview

The Super Resolution module contains a set of functions and classes that can be used to solve the problem of resolution enhancement. More…

// classes

class cv::superres::BroxOpticalFlow;
class cv::superres::DenseOpticalFlowExt;
class cv::superres::DualTVL1OpticalFlow;
class cv::superres::FarnebackOpticalFlow;
class cv::superres::FrameSource;
class cv::superres::PyrLKOpticalFlow;
class cv::superres::SuperResolution;

// global functions

Ptr<FrameSource>
cv::superres::createFrameSource_Camera(int deviceId = 0);

Ptr<FrameSource>
cv::superres::createFrameSource_Empty();

Ptr<FrameSource>
cv::superres::createFrameSource_Video(const String& fileName);

Ptr<FrameSource>
cv::superres::createFrameSource_Video_CUDA(const String& fileName);

Ptr<BroxOpticalFlow>
cv::superres::createOptFlow_Brox_CUDA();

Ptr<DualTVL1OpticalFlow>
cv::superres::createOptFlow_DualTVL1();

Ptr<DualTVL1OpticalFlow>
cv::superres::createOptFlow_DualTVL1_CUDA();

Ptr<FarnebackOpticalFlow>
cv::superres::createOptFlow_Farneback();

Ptr<FarnebackOpticalFlow>
cv::superres::createOptFlow_Farneback_CUDA();

Ptr<PyrLKOpticalFlow>
cv::superres::createOptFlow_PyrLK_CUDA();

Ptr<SuperResolution>
cv::superres::createSuperResolution_BTVL1();

Ptr<SuperResolution>
cv::superres::createSuperResolution_BTVL1_CUDA();

Detailed Documentation

The Super Resolution module contains a set of functions and classes that can be used to solve the problem of resolution enhancement. There are a few methods implemented, most of them are descibed in the papers [23] and [59].

Global Functions

Ptr<SuperResolution>
cv::superres::createSuperResolution_BTVL1()

Create Bilateral TV-L1 Super Resolution.

This class implements Super Resolution algorithm described in the papers [23] and [59].

Here are important members of the class that control the algorithm, which you can set after constructing the class instance:

  • int scale Scale factor.
  • int iterations Iteration count.
  • double tau Asymptotic value of steepest descent method.
  • double lambda Weight parameter to balance data term and smoothness term.
  • double alpha Parameter of spacial distribution in Bilateral-TV.
  • int btvKernelSize Kernel size of Bilateral-TV filter.
  • int blurKernelSize Gaussian blur kernel size.
  • double blurSigma Gaussian blur sigma.
  • int temporalAreaRadius Radius of the temporal search area.
  • Ptr <DenseOpticalFlowExt> opticalFlow Dense optical flow algorithm.