iteratively reduces noise while preserving edges in image.


assumes a regularization parameter value param.

Details and Options

  • TotalVariationFilter works with arbitrary 2D and 3D images, operating separately on each channel, as well as numerical data arrays of any rank.
  • In TotalVariationFilter[image,param], the value of regularization parameter param is typically in the range 0 to 1.
  • The following options can be specified:
  • MaxIterations30maximum number of iterations to be performed
    Method"Gaussian"type of noise to be removed
  • Possible Method settings include "Gaussian", "Laplacian", and "Poisson".
  • By default, Gaussian noise is assumed. For removing salt-and-pepper noise or impulse noise, the Laplacian noise model gives the best results. Poisson noise typically describes low-light images as well as various types of multiplicative noise. »


open allclose all

Basic Examples  (2)

Remove Poisson noise from a low-light photo:

Click for copyable input

Remove salt-and-pepper noise from a 3D image:

Click for copyable input

Scope  (3)

Generalizations & Extensions  (1)

Options  (2)

Applications  (1)

See Also

WienerFilter  MedianFilter  MeanShiftFilter  PeronaMalikFilter

Introduced in 2010
| Updated in 2012