# kornia.color¶

The functions in this section perform various color space conversions.

Note

Check a tutorial for color space conversions here.

## Grayscale¶

kornia.color.rgb_to_grayscale(image, rgb_weights=torch.tensor([0.299, 0.587, 0.114]))[source]

Convert a RGB image to grayscale version of image.

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

Parameters
• image (Tensor) – RGB image to be converted to grayscale with shape $$(*,3,H,W)$$.

• rgb_weights (Tensor, optional) – Weights that will be applied on each channel (RGB). The sum of the weights should add up to one. Default: torch.tensor([0.299, 0.587, 0.114])

Return type

Tensor

Returns

grayscale version of the image with shape $$(*,1,H,W)$$.

Note

See a working example here.

Example

>>> input = torch.rand(2, 3, 4, 5)
>>> gray = rgb_to_grayscale(input) # 2x1x4x5

kornia.color.bgr_to_grayscale(image)[source]

Convert a BGR image to grayscale.

The image data is assumed to be in the range of (0, 1). First flips to RGB, then converts.

Parameters

image (Tensor) – BGR image to be converted to grayscale with shape $$(*,3,H,W)$$.

Return type

Tensor

Returns

grayscale version of the image with shape $$(*,1,H,W)$$.

Example

>>> input = torch.rand(2, 3, 4, 5)
>>> gray = bgr_to_grayscale(input) # 2x1x4x5

kornia.color.grayscale_to_rgb(image)[source]

Convert a grayscale image to RGB version of image.

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

Parameters

image (Tensor) – grayscale image to be converted to RGB with shape $$(*,1,H,W)$$.

Return type

Tensor

Returns

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

Example

>>> input = torch.randn(2, 1, 4, 5)
>>> gray = grayscale_to_rgb(input) # 2x3x4x5

class kornia.color.GrayscaleToRgb[source]

Module to convert a grayscale image to RGB version of image.

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

Shape:
• image: $$(*, 1, H, W)$$

• output: $$(*, 3, H, W)$$

reference:

https://docs.opencv.org/4.0.1/de/d25/imgproc_color_conversions.html

Example

>>> input = torch.rand(2, 1, 4, 5)
>>> rgb = GrayscaleToRgb()
>>> output = rgb(input)  # 2x3x4x5

class kornia.color.RgbToGrayscale(rgb_weights=torch.tensor([0.299, 0.587, 0.114]))[source]

Module to convert a RGB image to grayscale version of image.

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

Shape:
• image: $$(*, 3, H, W)$$

• output: $$(*, 1, H, W)$$

reference:

https://docs.opencv.org/4.0.1/de/d25/imgproc_color_conversions.html

Example

>>> input = torch.rand(2, 3, 4, 5)
>>> gray = RgbToGrayscale()
>>> output = gray(input)  # 2x1x4x5

class kornia.color.BgrToGrayscale[source]

Module to convert a BGR image to grayscale version of image.

The image data is assumed to be in the range of (0, 1). First flips to RGB, then converts.

Shape:
• image: $$(*, 3, H, W)$$

• output: $$(*, 1, H, W)$$

reference:

https://docs.opencv.org/4.0.1/de/d25/imgproc_color_conversions.html

Example

>>> input = torch.rand(2, 3, 4, 5)
>>> gray = BgrToGrayscale()
>>> output = gray(input)  # 2x1x4x5


## RGB¶

Tip

kornia.color.rgb_to_bgr(image)[source]

Convert a RGB image to BGR.

Parameters

image (Tensor) – RGB Image to be converted to BGRof of shape $$(*,3,H,W)$$.

Return type

Tensor

Returns

BGR version of the image with shape of shape $$(*,3,H,W)$$.

Example

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

kornia.color.bgr_to_rgb(image)[source]

Convert a BGR image to RGB.

Parameters

image (Tensor) – BGR Image to be converted to BGR of shape $$(*,3,H,W)$$.

Return type

Tensor

Returns

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

Example

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

kornia.color.rgb_to_linear_rgb(image)[source]

Convert an sRGB image to linear RGB. Used in colorspace conversions.

Parameters

image (Tensor) – sRGB Image to be converted to linear RGB of shape $$(*,3,H,W)$$.

Return type

Tensor

Returns

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

Example

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

kornia.color.linear_rgb_to_rgb(image)[source]

Convert a linear RGB image to sRGB. Used in colorspace conversions.

Parameters

image (Tensor) – linear RGB Image to be converted to sRGB of shape $$(*,3,H,W)$$.

Return type

Tensor

Returns

sRGB version of the image with shape of shape $$(*,3,H,W)$$.

Example

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

class kornia.color.RgbToBgr[source]

Convert an image from RGB to BGR.

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

Returns

BGR version of the image.

Shape:
• image: $$(*, 3, H, W)$$

• output: $$(*, 3, H, W)$$

Example

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

class kornia.color.BgrToRgb[source]

Convert image from BGR 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: $$(*, 3, H, W)$$

Example

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

class kornia.color.LinearRgbToRgb[source]

Convert a linear RGB image to sRGB.

Applies gamma correction to linear RGB values, at the end of colorspace conversions, to get sRGB.

Returns

sRGB version of the image.

Shape:
• image: $$(*, 3, H, W)$$

• output: $$(*, 3, H, W)$$

Example

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


References

class kornia.color.RgbToLinearRgb[source]

Convert an image from sRGB to linear RGB.

Reverses the gamma correction of sRGB to get linear RGB values for colorspace conversions. The image data is assumed to be in the range of $$[0, 1]$$

Returns

Linear RGB version of the image.

Shape:
• image: $$(*, 3, H, W)$$

• output: $$(*, 3, H, W)$$

Example

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


References

## RGBA¶

Tip

kornia.color.bgr_to_rgba(image, alpha_val)[source]

Convert an image from BGR to RGBA.

Parameters
Return type

Tensor

Returns

RGBA version of the image with shape $$(*,4,H,W)$$.

Note

The current functionality is NOT supported by Torchscript.

Example

>>> input = torch.rand(2, 3, 4, 5)
>>> output = bgr_to_rgba(input, 1.) # 2x4x4x5

kornia.color.rgb_to_rgba(image, alpha_val)[source]

Convert an image from RGB to RGBA.

Parameters
• image (Tensor) – RGB Image to be converted to RGBA of shape $$(*,3,H,W)$$.

• alpha_val (float, torch.Tensor) – A float number for the alpha value or a tensor of shape $$(*,1,H,W)$$.

Return type

Tensor

Returns

RGBA version of the image with shape $$(*,4,H,W)$$.

Note

The current functionality is NOT supported by Torchscript.

Example

>>> input = torch.rand(2, 3, 4, 5)
>>> output = rgb_to_rgba(input, 1.) # 2x4x4x5

kornia.color.rgba_to_rgb(image)[source]

Convert an image from RGBA to RGB.

Parameters

image (Tensor) – RGBA Image to be converted to RGB of shape $$(*,4,H,W)$$.

Return type

Tensor

Returns

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

Example

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

kornia.color.rgba_to_bgr(image)[source]

Convert an image from RGBA to BGR.

Parameters

image (Tensor) – RGBA Image to be converted to BGR of shape $$(*,4,H,W)$$.

Return type

Tensor

Returns

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

Example

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

class kornia.color.RgbToRgba(alpha_val)[source]

Convert an image from RGB to RGBA.

Add an alpha channel to existing RGB image.

Parameters

alpha_val (Union[float, Tensor]) – A float number for the alpha value or a tensor of shape $$(*,1,H,W)$$.

Returns

RGBA version of the image with shape $$(*,4,H,W)$$.

Return type

torch.Tensor

Shape:
• image: $$(*, 3, H, W)$$

• output: $$(*, 4, H, W)$$

Note

The current functionality is NOT supported by Torchscript.

Example

>>> input = torch.rand(2, 3, 4, 5)
>>> rgba = RgbToRgba(1.)
>>> output = rgba(input)  # 2x4x4x5

class kornia.color.BgrToRgba(alpha_val)[source]

Convert an image from BGR to RGBA.

Add an alpha channel to existing RGB image.

Parameters

alpha_val (Union[float, Tensor]) – A float number for the alpha value or a tensor of shape $$(*,1,H,W)$$.

Returns

RGBA version of the image with shape $$(*,4,H,W)$$.

Shape:
• image: $$(*, 3, H, W)$$

• output: $$(*, 4, H, W)$$

Note

The current functionality is NOT supported by Torchscript.

Example

>>> input = torch.rand(2, 3, 4, 5)
>>> rgba = BgrToRgba(1.)
>>> output = rgba(input)  # 2x4x4x5

class kornia.color.RgbaToRgb[source]

Convert an image from RGBA to RGB.

Remove an alpha channel from RGB image.

Returns

RGB version of the image.

Shape:
• image: $$(*, 4, H, W)$$

• output: $$(*, 3, H, W)$$

Example

>>> input = torch.rand(2, 4, 4, 5)
>>> rgba = RgbaToRgb()
>>> output = rgba(input)  # 2x3x4x5

class kornia.color.RgbaToBgr[source]

Convert an image from RGBA to BGR.

Remove an alpha channel from BGR image.

Returns

BGR version of the image.

Shape:
• image: $$(*, 4, H, W)$$

• output: $$(*, 3, H, W)$$

Example

>>> input = torch.rand(2, 4, 4, 5)
>>> rgba = RgbaToBgr()
>>> output = rgba(input)  # 2x3x4x5


## HLS¶

kornia.color.rgb_to_hls(image, eps=1e-08)[source]

Convert a RGB image to HLS.

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

NOTE: this method cannot be compiled with JIT in pytohrch < 1.7.0

Parameters
• image (Tensor) – RGB image to be converted to HLS with shape $$(*, 3, H, W)$$.

• eps (float, optional) – epsilon value to avoid div by zero. Default: 1e-08

Return type

Tensor

Returns

HLS version of the image with shape $$(*, 3, H, W)$$.

Example

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

kornia.color.hls_to_rgb(image)[source]

Convert a HLS image to RGB.

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

Parameters

image (Tensor) – HLS image to be converted to RGB with shape $$(*, 3, H, W)$$.

Return type

Tensor

Returns

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

Example

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

class kornia.color.RgbToHls[source]

Convert an image from RGB to HLS.

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

Returns

HLS version of the image.

Shape:
• image: $$(*, 3, H, W)$$

• output: $$(*, 3, H, W)$$

Examples

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

class kornia.color.HlsToRgb[source]

Convert an image from HLS to RGB.

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

Returns

RGB version of the image.

Shape:
• input: $$(*, 3, H, W)$$

• output: $$(*, 3, H, W)$$

Reference:

https://en.wikipedia.org/wiki/HSL_and_HSV

Examples

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


## HSV¶

kornia.color.rgb_to_hsv(image, eps=1e-08)[source]

Convert an image from RGB to HSV.

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

Parameters
• image (Tensor) – RGB Image to be converted to HSV with shape of $$(*, 3, H, W)$$.

• eps (float, optional) – scalar to enforce numarical stability. Default: 1e-08

Return type

Tensor

Returns

HSV version of the image with shape of $$(*, 3, H, W)$$. The H channel values are in the range 0..2pi. S and V are in the range 0..1.

Note

See a working example here.

Example

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

kornia.color.hsv_to_rgb(image)[source]

Convert an image from HSV to RGB.

The H channel values are assumed to be in the range 0..2pi. S and V are in the range 0..1.

Parameters

image (Tensor) – HSV Image to be converted to HSV with shape of $$(*, 3, H, W)$$.

Return type

Tensor

Returns

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

Example

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

class kornia.color.RgbToHsv(eps=1e-06)[source]

Convert an image from RGB to HSV.

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

Parameters

eps (float, optional) – scalar to enforce numarical stability. Default: 1e-06

Returns

HSV version of the image.

Shape:
• image: $$(*, 3, H, W)$$

• output: $$(*, 3, H, W)$$

Example

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

class kornia.color.HsvToRgb[source]

Convert an image from HSV to RGB.

H channel values are assumed to be in the range 0..2pi. S and V are in the range 0..1.

Returns

RGB version of the image.

Shape:
• image: $$(*, 3, H, W)$$

• output: $$(*, 3, H, W)$$

Example

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


## LUV¶

kornia.color.rgb_to_luv(image, eps=1e-12)[source]

Convert a RGB image to Luv.

The image data is assumed to be in the range of $$[0, 1]$$. Luv color is computed using the D65 illuminant and Observer 2.

Parameters
• image (Tensor) – RGB Image to be converted to Luv with shape $$(*, 3, H, W)$$.

• eps (float, optional) – for numerically stability when dividing. Default: 1e-12

Return type

Tensor

Returns

Luv version of the image with shape $$(*, 3, H, W)$$.

Example

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

kornia.color.luv_to_rgb(image, eps=1e-12)[source]

Convert a Luv image to RGB.

Parameters
• image (Tensor) – Luv image to be converted to RGB with shape $$(*, 3, H, W)$$.

• eps (float, optional) – for numerically stability when dividing. Default: 1e-12

Return type

Tensor

Returns

Luv version of the image with shape $$(*, 3, H, W)$$.

Example

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

class kornia.color.RgbToLuv[source]

Convert an image from RGB to Luv.

The image data is assumed to be in the range of $$[0, 1]$$. Luv color is computed using the D65 illuminant and Observer 2.

Returns

Luv version of the image.

Shape:
• image: $$(*, 3, H, W)$$

• output: $$(*, 3, H, W)$$

Examples

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

Reference:
class kornia.color.LuvToRgb[source]

Convert an image from Luv to RGB.

Returns

RGB version of the image.

Shape:
• image: $$(*, 3, H, W)$$

• output: $$(*, 3, H, W)$$

Examples

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


References

## Lab¶

Tip

kornia.color.rgb_to_lab(image)[source]

Convert a RGB image to Lab.

The image data is assumed to be in the range of $$[0, 1]$$. Lab color is computed using the D65 illuminant and Observer 2.

Parameters

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

Return type

Tensor

Returns

Lab version of the image with shape $$(*, 3, H, W)$$. The L channel values are in the range 0..100. a and b are in the range -127..127.

Example

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

kornia.color.lab_to_rgb(image, clip=True)[source]

Convert a Lab image to RGB.

Parameters
• image (Tensor) – Lab image to be converted to RGB with shape $$(*, 3, H, W)$$.

• clip (bool, optional) – Whether to apply clipping to insure output RGB values in range $$[0, 1]$$. Default: True

Return type

Tensor

Returns

Lab version of the image with shape $$(*, 3, H, W)$$.

Example

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

class kornia.color.RgbToLab[source]

Convert an image from RGB to Lab.

The image data is assumed to be in the range of $$[0, 1]$$. Lab color is computed using the D65 illuminant and Observer 2.

Returns

Lab version of the image.

Shape:
• image: $$(*, 3, H, W)$$

• output: $$(*, 3, H, W)$$

Examples

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

Reference:
class kornia.color.LabToRgb[source]

Convert an image from Lab to RGB.

Returns

RGB version of the image. Range may not be in $$[0, 1]$$.

Shape:
• image: $$(*, 3, H, W)$$

• output: $$(*, 3, H, W)$$

Examples

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


References

## YCbCr¶

kornia.color.rgb_to_ycbcr(image)[source]

Convert an RGB image to YCbCr.

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.ycbcr_to_rgb(image)[source]

Convert an YCbCr image to RGB.

The image data is assumed to be in the range of (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

class kornia.color.YcbcrToRgb[source]

Convert an image from 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

class kornia.color.RgbToYcbcr[source]

Convert an image from 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


## YUV¶

kornia.color.rgb_to_yuv(image)[source]

Convert an RGB image to YUV.

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

Parameters

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

Return type

Tensor

Returns

YUV version of the image with shape $$(*, 3, H, W)$$.

Example

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

kornia.color.yuv_to_rgb(image)[source]

Convert an YUV image to RGB.

The image data is assumed to be in the range of (0, 1) for luma and (-0.5, 0.5) for chroma.

Parameters

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

Return type

Tensor

Returns

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

Example

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

class kornia.color.RgbToYuv[source]

Convert an image from RGB to YUV.

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

Returns

YUV version of the image.

Shape:
• image: $$(*, 3, H, W)$$

• output: $$(*, 3, H, W)$$

Examples

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

Reference::
class kornia.color.YuvToRgb[source]

Convert an image from YUV to RGB.

The image data is assumed to be in the range of (0, 1) for luma and (-0.5, 0.5) for chroma.

Returns

RGB version of the image.

Shape:
• image: $$(*, 3, H, W)$$

• output: $$(*, 3, H, W)$$

Examples

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


## YUV420¶

Tip

kornia.color.rgb_to_yuv420(image)[source]

Convert an RGB image to YUV 420 (subsampled).

The image data is assumed to be in the range of (0, 1). Input need to be padded to be evenly divisible by 2 horizontal and vertical. This function will output chroma siting (0.5,0.5)

Parameters

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

Return type
Returns

A Tensor containing the Y plane with shape $$(*, 1, H, W)$$ A Tensor containing the UV planes with shape $$(*, 2, H/2, W/2)$$

Example

>>> input = torch.rand(2, 3, 4, 6)
>>> output = rgb_to_yuv420(input)  # (2x1x4x6, 2x2x2x3)

kornia.color.yuv420_to_rgb(imagey, imageuv)[source]

Convert an YUV420 image to RGB.

The image data is assumed to be in the range of (0, 1) for luma and (-0.5, 0.5) for chroma. Input need to be padded to be evenly divisible by 2 horizontal and vertical. This function assumed chroma siting is (0.5, 0.5)

Parameters
• imagey (Tensor) – Y (luma) Image plane to be converted to RGB with shape $$(*, 1, H, W)$$.

• imageuv (Tensor) – UV (chroma) Image planes to be converted to RGB with shape $$(*, 2, H/2, W/2)$$.

Return type

Tensor

Returns

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

Example

>>> inputy = torch.rand(2, 1, 4, 6)
>>> inputuv = torch.rand(2, 2, 2, 3)
>>> output = yuv420_to_rgb(inputy, inputuv)  # 2x3x4x6

class kornia.color.RgbToYuv420[source]

Convert an image from RGB to YUV420.

The image data is assumed to be in the range of (0, 1). Width and Height evenly divisible by 2.

Returns

YUV420 version of the image.

Shape:
• image: $$(*, 3, H, W)$$

• output: $$(*, 1, H, W)$$ and $$(*, 2, H/2, W/2)$$

Examples

>>> yuvinput = torch.rand(2, 3, 4, 6)
>>> yuv = RgbToYuv420()
>>> output = yuv(yuvinput)  # # (2x1x4x6, 2x1x2x3)

Reference::
class kornia.color.Yuv420ToRgb[source]

Convert an image from YUV to RGB.

The image data is assumed to be in the range of (0, 1) for luma and (-0.5, 0.5) for chroma. Width and Height evenly divisible by 2.

Returns

RGB version of the image.

Shape:
• imagey: $$(*, 1, H, W)$$

• imageuv: $$(*, 2, H/2, W/2)$$

• output: $$(*, 3, H, W)$$

Examples

>>> inputy = torch.rand(2, 1, 4, 6)
>>> inputuv = torch.rand(2, 2, 2, 3)
>>> rgb = Yuv420ToRgb()
>>> output = rgb(inputy, inputuv)  # 2x3x4x6


## YUV422¶

Tip

kornia.color.rgb_to_yuv422(image)[source]

Convert an RGB image to YUV 422 (subsampled).

The image data is assumed to be in the range of (0, 1). Input need to be padded to be evenly divisible by 2 vertical. This function will output chroma siting (0.5)

Parameters

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

Return type
Returns

A Tensor containing the Y plane with shape $$(*, 1, H, W)$$ A Tensor containing the UV planes with shape $$(*, 2, H, W/2)$$

Example

>>> input = torch.rand(2, 3, 4, 6)
>>> output = rgb_to_yuv420(input)  # (2x1x4x6, 2x1x4x3)

kornia.color.yuv422_to_rgb(imagey, imageuv)[source]

Convert an YUV422 image to RGB.

The image data is assumed to be in the range of (0, 1) for luma and (-0.5, 0.5) for chroma. Input need to be padded to be evenly divisible by 2 vertical. This function assumed chroma siting is (0.5)

Parameters
• imagey (Tensor) – Y (luma) Image plane to be converted to RGB with shape $$(*, 1, H, W)$$.

• imageuv (Tensor) – UV (luma) Image planes to be converted to RGB with shape $$(*, 2, H, W/2)$$.

Return type

Tensor

Returns

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

Example

>>> inputy = torch.rand(2, 1, 4, 6)
>>> inputuv = torch.rand(2, 2, 2, 3)
>>> output = yuv420_to_rgb(inputy, inputuv)  # 2x3x4x5

class kornia.color.RgbToYuv422[source]

Convert an image from RGB to YUV422.

The image data is assumed to be in the range of (0, 1). Width evenly disvisible by 2.

Returns

YUV422 version of the image.

Shape:
• image: $$(*, 3, H, W)$$

• output: $$(*, 1, H, W)$$ and $$(*, 2, H, W/2)$$

Examples

>>> yuvinput = torch.rand(2, 3, 4, 6)
>>> yuv = RgbToYuv422()
>>> output = yuv(yuvinput)  # # (2x1x4x6, 2x2x4x3)

Reference::
class kornia.color.Yuv422ToRgb[source]

Convert an image from YUV to RGB.

The image data is assumed to be in the range of (0, 1) for luma and (-0.5, 0.5) for chroma. Width evenly divisible by 2.

Returns

RGB version of the image.

Shape:
• imagey: $$(*, 1, H, W)$$

• imageuv: $$(*, 2, H, W/2)$$

• output: $$(*, 3, H, W)$$

Examples

>>> inputy = torch.rand(2, 1, 4, 6)
>>> inputuv = torch.rand(2, 2, 4, 3)
>>> rgb = Yuv422ToRgb()
>>> output = rgb(inputy, inputuv)  # 2x3x4x6


## XYZ¶

kornia.color.rgb_to_xyz(image)[source]

Convert a RGB image to XYZ.

Parameters

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

Return type

Tensor

Returns

XYZ version of the image with shape $$(*, 3, H, W)$$.

Example

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

kornia.color.xyz_to_rgb(image)[source]

Convert a XYZ image to RGB.

Parameters

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

Return type

Tensor

Returns

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

Example

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

class kornia.color.RgbToXyz[source]

Convert an image from RGB to XYZ.

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

Returns

XYZ version of the image.

Shape:
• image: $$(*, 3, H, W)$$

• output: $$(*, 3, H, W)$$

Examples

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

Reference:
class kornia.color.XyzToRgb[source]

Converts an image from XYZ to RGB.

Returns

RGB version of the image.

Shape:
• image: $$(*, 3, H, W)$$

• output: $$(*, 3, H, W)$$

Examples

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

Reference:

## Bayer RAW¶

class kornia.color.CFA(value)[source]

Define the configuration of the color filter array.

So far only bayer images is supported and the enum sets the pixel order for bayer. Note that this can change due to things like rotations and cropping of images. Take care if including the translations in pipeline. This implementations is optimized to be reasonably fast, look better than simple nearest neighbour. On top of this care is taken to make it reversible going raw -> rgb -> raw. the raw samples remain intact during conversion and only unknown samples are interpolated.

The names are based on the OpenCV convention where the BG indicates pixel 1,1 (counting from 0,0) is blue and its neighbour to the right is green. In that case the top left pixel is red. Other options are GB, RG and GR

reference:

https://en.wikipedia.org/wiki/Color_filter_array

BG = 0
GB = 1
GR = 3
RG = 2
kornia.color.rgb_to_raw(image, cfa)[source]

Convert a RGB image to RAW version of image with the specified color filter array.

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

Parameters
• image (Tensor) – RGB image to be converted to bayer raw with shape $$(*,3,H,W)$$.

• cfa (CFA) – Which color filter array do we want the output to mimic. I.e. which pixels are red/green/blue.

Return type

Tensor

Returns

raw version of the image with shape $$(*,1,H,W)$$.

Example

>>> rgbinput = torch.rand(2, 3, 4, 6)
>>> raw = rgb_to_raw(rgbinput, CFA.BG) # 2x1x4x6

kornia.color.raw_to_rgb(image, cfa)[source]

Convert a raw bayer image to RGB version of image.

We are assuming a CFA with 2 green, 1 red, 1 blue. A bilinear interpolation is used for R/G and a fix convolution for the green pixels. To simplify calculations we expect the Height Width to be evenly divisible by 2.

The image data is assumed to be in the range of (0, 1). Image H/W is assumed to be evenly divisible by 2. for simplicity reasons

Parameters
Return type

Tensor

Returns

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

Example

>>> rawinput = torch.randn(2, 1, 4, 6)
>>> rgb = raw_to_rgb(rawinput, CFA.RG) # 2x3x4x6

class kornia.color.RawToRgb(cfa)[source]

Module to convert a bayer raw image to RGB version of image.

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

Shape:
• image: $$(*, 1, H, W)$$

• output: $$(*, 3, H, W)$$

Example

>>> rawinput = torch.rand(2, 1, 4, 6)
>>> rgb = RawToRgb(CFA.RG)
>>> output = rgb(rawinput)  # 2x3x4x5

class kornia.color.RgbToRaw(cfa)[source]

Module to convert a RGB image to bayer raw version of image.

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

Shape:
• image: $$(*, 3, H, W)$$

• output: $$(*, 1, H, W)$$

reference:

https://docs.opencv.org/4.0.1/de/d25/imgproc_color_conversions.html

Example

>>> rgbinput = torch.rand(2, 3, 4, 6)
>>> raw = RgbToRaw(CFA.GB)
>>> output = raw(rgbinput)  # 2x1x4x6