You're right, it would be a fun side effect to see the color change between different scenes :) I guess there's not enough in commercial interest in fixing these problems, but it can be probably done with the current algorithms. Precise 3D reconstruction is much more important than colour reconstruction.

>it would be a fun side effect to see the color change between different scenes :)

Now that's a horse of a different color[0]!

[0] http://oz.wikia.com/wiki/Horse_of_a_Different_Color

Would it be possible to have some sort of semantic naming coupled to it 'the car in this scene is red', that could be fixed by humans, maybe even by talking to the NN? That's when this stuff starts getting fun IMO - human language together with superhuman domain knowledge.

Or even using the previously processed frames as reference the next time the shot appears

I'd imagine that many people wouldn't even notice (unless the truck's color is part of the plot)

Truck's color can not be part of the plot, its a B&W movie!

Protagonist: "Do you see that red truck?" light blue truck rolls through the scene

Maybe it's about a truck painting shop, and every time they paint something, it either doesn't change color, or get a color different from what the customer ordered. I would watch that.

You mean you would watch paint dry?

Actually, someone recently filmed exactly that - a 10-hour film of paint drying, as a protest against film censorship. The British Board of Film Classification awarded it a "U" rating: universal/suitable for all.

http://www.telegraph.co.uk/film/movie-news/paint-drying-bbfc...

It would have been funny to splice in a couple frames of porn throughout, Fight Club-style.

Are there any other issues or advantages that you're able to see that would be unique to movies? While I'm unable to think of a use, seems like there's the potiental for side channel analyis via music, dialog, background-noises, scripts, etc.

Script analysis would take much more effort probably, but it could work if the colour is in the movie script...in that case object detection gets important as well. Just using more training data to cover all the dog breeds and car colours would help a bit though.