vpi.TemporalNoiseReduction.__call__

TemporalNoiseReduction.__call__(self: vpi.TemporalNoiseReduction, input: vpi.Image, *, stream: vpi.Stream = None, preset: vpi.TNRPreset = vpi.TNRPreset.DEFAULT, strength: float = 0.5) → vpi.Image

Runs the TNR algorithm on the input image.

Hint

The temporal noise reduction (TNR) algorithm uses two frames to reduce noise in time (frame sequence), the current and previous frame. The input image is always the current frame and, from the second call forward, the previous image is provided automatically.

See also

Refer to the algorithm explanation for more details and usage examples.

Parameters

  • input (vpi.Image) – Input image frame (with noise) to be processed by the algorithm.

  • preset (vpi.TNRPreset, optional) – The preset to be used by the algorithm.

  • strength (float, optional) – The noise-reduction strength.

  • stream (vpi.Stream, optional) – The stream to be used by the algorithm.

Returns

The output image frame (with noise reduced).

Return type

vpi.Image

Caution

Restrictions to several arguments may apply. Check the C API references of the submit function and the group concepts for more details.