How hard would it be to do the opposite? point a camera at the stars in multiple directions, recognise the angle of various constellations, and use that to work out your location?
Easy enough, since this is how celestial navigation works, especially as we have very accurate clocks. You can get latitude from image declination and longitude from time, provided your clock is set from a good reference. In theory you only need one image pointed straight up to estimate declination. You’ll probably have an uncertainty on the order of miles.
