Q1 - Do we need to consider other pixels from the frame of the unobserved grid?

Q1 - Do we need to consider other pixels from the frame of the unobserved grid?

student (guest) 28 Apr 2017 09:43

Hi,
Some students claimed that when completing the unobserved pixels in the picture we need to consider only the frame pixels surrounding them, because it's a Markov Network and therefore the rest of the observed pixels are separated by that frame.

I don't understand why this is correct. according to that claim the same frame from two different pictures will give us the same completion - isn't that wrong? if not - why?

and if we do take in account some more far away pixels outside of the frame, won't we get more accurate and correct results, since we take in account more information about the picture?

Roey (guest) 28 Apr 2017 11:09

It's not a matter of 'correct' vs 'incorrect', it's a question of what is the suggested model. A simple Markovian models suggests that the unobserved pixels only depend on the 'frame', since (as you mentioned) the frame separates the unobserved pixels from the observed ones.
Using a Markov model of higher order will (probably) give better results, but this is not the model we are asked to implement.
If you also take NLP, think about a first-order Markov model for sentence completion. This model suggests that the next work only depends on the current word. This will clearly give inaccurate results in most cases, but this is the definition of the model.