1
$\begingroup$

In deep learning, an image is said to contain two types of features. One is the content of the image and the other is the style of the image.

Deep neural networks are generally used to obtain both content representation and style representation of an image. So, one can roughly define the style and content representations of an image using deep neural networks.

Research papers generally show foreground objects (under consideration or focus) in an image as the content of the image and the background (or background objects such as sky etc.) as the style of the image.

If we need to define the content and style of an image without using deep neural networks, then what can be the definitions for the content and style of an image?

$\endgroup$
1
  • 1
    $\begingroup$ This question is related to AI because we are using AI to extract content and style vectors from images. How are these vectors distinguished - what is the difference between one and the other? Why does combining the style vector from Starry Night and the content vector from the Neckarfront photograph give us a Starry-Night-style painting of Neckarfront instead of a realistic photograph of a starry night? $\endgroup$
    – user253751
    Sep 8 at 10:25

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.