Semantic Photo Synthesis

dc.contributor.authorJohnson, M.en_US
dc.contributor.authorBrostow, G. J.en_US
dc.contributor.authorShotton, J.en_US
dc.contributor.authorArandjelovic, O.en_US
dc.contributor.authorKwatra, V.en_US
dc.contributor.authorCipolla, R.en_US
dc.date.accessioned2015-02-21T14:31:15Z
dc.date.available2015-02-21T14:31:15Z
dc.date.issued2006en_US
dc.description.abstractComposite images are synthesized from existing photographs by artists who make concept art, e.g., storyboards for movies or architectural planning. Current techniques allow an artist to fabricate such an image by digitally splicing parts of stock photographs. While these images serve mainly to quickly convey how a scene should look, their production is laborious. We propose a technique that allows a person to design a new photograph with substantially less effort. This paper presents a method that generates a composite image when a user types in nouns, such as boat and sand. The artist can optionally design an intended image by specifying other constraints. Our algorithm formulates the constraints as queries to search an automatically annotated image database. The desired photograph, not a collage, is then synthesized using graph-cut optimization, optionally allowing for further user interaction to edit or choose among alternative generated photos. An implementation of our approach, shown in the associated video, demonstrates our contributions of (1) a method for creating specific images with minimal human effort, and (2) a combined algorithm for automatically building an image library with semantic annotations from any photo collection.en_US
dc.description.number3en_US
dc.description.seriesinformationComputer Graphics Forumen_US
dc.description.volume25en_US
dc.identifier.doi10.1111/j.1467-8659.2006.00960.xen_US
dc.identifier.issn1467-8659en_US
dc.identifier.pages407-413en_US
dc.identifier.urihttps://doi.org/10.1111/j.1467-8659.2006.00960.xen_US
dc.publisherThe Eurographics Association and Blackwell Publishing, Incen_US
dc.titleSemantic Photo Synthesisen_US
Files
Collections