Hm, it's not a great algorithm compared to some others that have been discussed here. There was a crazy one last year where it could replace entire large regions of the photo automatically and there was no indication anything had been altered.

This looks like a poorly done paste and smear job. For a student's semester project, which I suppose it is, it's great.

Seam carving? http://www.youtube.com/watch?v=vIFCV2spKtg

Person-silhouetting seems more difficult to do well than content-replacing. I wonder how this falls apart in complex scenarios? Still, an interesting idea.

Patch match: http://www.youtube.com/watch?v=otAbvtiabeY

Yes, that's the main one I was thinking of, thanks. The seam one also I had in mind.

Yeah agreed. Smooth replacement of content is great, but I think you could easily build seam carving into this. The hard part is doing the person-detection in the first place.

On an unrelated note, "Belongie" is a fantastic name.

Yes, I know it's French :(

That's cool, but do they have a "pedestrian" one too?