Super Resolution#

Detailed Description#

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 described in the papers [95] and [219] .

Classes#

Function Documentation#

createFrameSource_Camera()#

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

#include <opencv2/superres.hpp>

createFrameSource_Empty()#

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

#include <opencv2/superres.hpp>

createFrameSource_Video()#

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

#include <opencv2/superres.hpp>

createFrameSource_Video_CUDA()#

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

#include <opencv2/superres.hpp>

createOptFlow_Brox_CUDA()#

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

#include <opencv2/superres/optical_flow.hpp>

createOptFlow_DualTVL1()#

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

#include <opencv2/superres/optical_flow.hpp>

createOptFlow_DualTVL1_CUDA()#

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

#include <opencv2/superres/optical_flow.hpp>

createOptFlow_Farneback()#

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

#include <opencv2/superres/optical_flow.hpp>

createOptFlow_Farneback_CUDA()#

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

#include <opencv2/superres/optical_flow.hpp>

createOptFlow_PyrLK_CUDA()#

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

#include <opencv2/superres/optical_flow.hpp>

createSuperResolution_BTVL1()#

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

#include <opencv2/superres.hpp>

Create Bilateral TV-L1 Super Resolution.

This class implements Super Resolution algorithm described in the papers [95] and [219] .

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 opticalFlow Dense optical flow algorithm.

createSuperResolution_BTVL1_CUDA()#

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

#include <opencv2/superres.hpp>