# Images as Markov chains

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.