On: 3-Sweep: Extracting Editable Objects from a Single...

[EGreg]

This is awesome - but how do they reconstruct the backgrounds that the objects previously obscured? There must be more photos?

[dharma1 → EGreg]

i thought about that too - i think the background is simply a mirror image of the foreground, and that the object 3d shape is symmetrical

[EGreg → dharma1]

apparently they are using some other algorithm to do this - even more impressive!

however, it seems strange in the first example how mountain ranges appear where none were before... how did the algos know to put it there?

[abrichr → EGreg]

This is the PatchMatch algorithm:

http://gfx.cs.princeton.edu/pubs/Barnes_2009_PAR/