I have seen literature on representing black and white images as probability distributions and then computing "distances" between them, for example, in optimal transport.

I was wondering if there is any literature on representing images as the stationary distribution of a Markov chain. For example, you can imagine a Markov chain on a 2-d lattice that prefers jumping to nearby lattice points and the transition probabilities are adjusted so that the stationary distribution is exactly proportional to the pixel intensity of the image.


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.