Skip to content

Pixel Manipulation

Source

N2V manipulation functions for PyTorch.

median_manipulate(batch, mask_pixel_percentage, subpatch_size=11, struct_params=None, rng=None)

Manipulate pixels by replacing them with the median of their surrounding subpatch.

N2V2 version, manipulated pixels are selected randomly away from a grid with an approximate uniform probability to be selected across the whole patch.

If struct_params is not None, an additional structN2V mask is applied to the data, replacing the pixels in the mask with random values (excluding the pixel already manipulated).

Parameters:

  • batch (Tensor) –

    Image patch, 2D or 3D, shape (y, x) or (z, y, x).

  • mask_pixel_percentage (float) –

    Approximate percentage of pixels to be masked.

  • subpatch_size (int, default: 11 ) –

    Size of the subpatch the new pixel value is sampled from, by default 11.

  • struct_params (StructMaskParameters or None, default: None ) –

    Parameters for the structN2V mask (axis and span).

  • rng (default_generator or None, default: None ) –

    Random number generator, by default None.

Returns:

  • tuple[Tensor, Tensor, Tensor] –

    tuple containing the manipulated patch, the original patch and the mask.

uniform_manipulate(patch, mask_pixel_percentage, subpatch_size=11, remove_center=True, struct_params=None, rng=None)

Manipulate pixels by replacing them with a neighbor values.

TODO add more details, especially about batch

Manipulated pixels are selected uniformly selected in a subpatch, away from a grid with an approximate uniform probability to be selected across the whole patch. If struct_params is not None, an additional structN2V mask is applied to the data, replacing the pixels in the mask with random values (excluding the pixel already manipulated).

Parameters:

  • patch (Tensor) –

    Image patch, 2D or 3D, shape (y, x) or (z, y, x). # TODO batch and channel.

  • mask_pixel_percentage (float) –

    Approximate percentage of pixels to be masked.

  • subpatch_size (int, default: 11 ) –

    Size of the subpatch the new pixel value is sampled from, by default 11.

  • remove_center (bool, default: True ) –

    Whether to remove the center pixel from the subpatch, by default True.

  • struct_params (StructMaskParameters or None, default: None ) –

    Parameters for the structN2V mask (axis and span).

  • rng (default_generator or None, default: None ) –

    Random number generator.

Returns:

  • tuple[Tensor, Tensor] –

    tuple containing the manipulated patch and the corresponding mask.