YCbCr#

Functions#

kornia.color.rgb_to_ycbcr(image)[source]#

Convert an RGB image to YCbCr.

_images/rgb_to_ycbcr.png
Convention:

Channels are Y, Cb, Cr at axis -3. RGB inputs and all output channels use unit-range full-range values.

Parameters:

image (Tensor) – RGB Image to be converted to YCbCr with shape \((*, 3, H, W)\).

Return type:

Tensor

Returns:

YCbCr version of the image with shape \((*, 3, H, W)\).

Examples

>>> input = torch.rand(2, 3, 4, 5)
>>> output = rgb_to_ycbcr(input)  # 2x3x4x5
kornia.color.rgb_to_y(image)[source]#

Convert an RGB image to Y.

Convention:

Returns the Y channel from the unit-range full-range YCbCr convention used by rgb_to_ycbcr.

Parameters:

image (Tensor) – RGB Image to be converted to Y with shape \((*, 3, H, W)\).

Return type:

Tensor

Returns:

Y version of the image with shape \((*, 1, H, W)\).

Examples

>>> input = torch.rand(2, 3, 4, 5)
>>> output = rgb_to_y(input)  # 2x1x4x5
kornia.color.ycbcr_to_rgb(image)[source]#

Convert an YCbCr image to RGB.

The image data is assumed to be in the range of (0, 1).

Convention:

Expects unit-range, full-range Y, Cb, Cr channels at axis -3 as produced by rgb_to_ycbcr. The final RGB result is clamped to [0, 1].

Parameters:

image (Tensor) – YCbCr Image to be converted to RGB with shape \((*, 3, H, W)\).

Return type:

Tensor

Returns:

RGB version of the image with shape \((*, 3, H, W)\).

Examples

>>> input = torch.rand(2, 3, 4, 5)
>>> output = ycbcr_to_rgb(input)  # 2x3x4x5

Modules#

class kornia.color.RgbToYcbcr(*args, **kwargs)[source]#

Convert an image from RGB to YCbCr.

See the Convention block on rgb_to_ycbcr().

The image data is assumed to be in the range of (0, 1).

Returns:

YCbCr version of the image.

Shape:
  • image: \((*, 3, H, W)\)

  • output: \((*, 3, H, W)\)

Examples

>>> input = torch.rand(2, 3, 4, 5)
>>> ycbcr = RgbToYcbcr()
>>> output = ycbcr(input)  # 2x3x4x5
class kornia.color.YcbcrToRgb(*args, **kwargs)[source]#

Convert an image from YCbCr to Rgb.

See the Convention block on ycbcr_to_rgb().

The image data is assumed to be in the range of (0, 1).

Returns:

RGB version of the image.

Shape:
  • image: \((*, 3, H, W)\)

  • output: \((*, 3, H, W)\)

Examples

>>> input = torch.rand(2, 3, 4, 5)
>>> rgb = YcbcrToRgb()
>>> output = rgb(input)  # 2x3x4x5