Warning: This project is deprecated. TensorFlow Addons has stopped development, The project will only be providing minimal maintenance releases until May 2024. See the full announcement here or on github.

tfa.image.blend

Blend image1 and image2 using factor.

tfa.image.blend(
    image1: tfa.types.TensorLike,
    image2: tfa.types.TensorLike,
    factor: tfa.types.Number
) -> tf.Tensor

Factor can be above 0.0. A value of 0.0 means only image1 is used. A value of 1.0 means only image2 is used. A value between 0.0 and 1.0 means we linearly interpolate the pixel values between the two images. A value greater than 1.0 "extrapolates" the difference between the two pixel values, and we clip the results to values between 0 and 255.

image1 An image Tensor of shape (num_rows, num_columns, num_channels) (HWC), or (num_rows, num_columns) (HW), or (num_channels, num_rows, num_columns) (CHW).
image2 An image Tensor of shape (num_rows, num_columns, num_channels) (HWC), or (num_rows, num_columns) (HW), or (num_channels, num_rows, num_columns).
factor A floating point value or Tensor of type tf.float32 above 0.0.

A blended image Tensor of tf.float32.