Curvature Flow

Class: NodeImageMinMaxCurvatureFlowFilter

Node Icon

Curvature driven image denoising algorithm. Iso-brightness contours in the grayscale input image are viewed as a level set. The level set is then evolved using a curvature-based speed function.

In min/max curvature flow, movement is turned on or off depending on the scale of the noise one wants to remove. Switching depends on the average image value of a region, the stencil radius, governs the scale of the noise to be removed.



Input image.

Type: Image4DFloat, Required, Single



Resulting image.

Type: Image4DFloat


Time Step Number

Set the timestep parameter.

Iterations Integer

Set the number of iterations.

Stencil Radius Integer

The scale of the noise to be removed.


  1. “Level Set Methods and Fast Marching Methods”, J.A.Sethian, Cambridge Press, Chapter 16, Second edition, 1999.
  2. “The Insight Segmentation and Registration Toolkit”