We generate 3D scenes that allow the same activities as real environments captured through noisy and incomplete 3D scans. Our core contribution is a new scene synthesis technique which, conditioned on a coarse geometric scene representation, models functionally similar scenes using prior knowledge learned from a scene database.

Matthew Fisher, Stanford University
Matthias Nießner, Stanford University
Manolis Savva, Stanford University
Yangyan Li, Stanford University
Pat Hanrahan, Stanford University