Faking it: simulating background blur in portrait photography using a coarse depth map estimation from a single image

Abstract

In this work we simulate background blur in photographs through a coarse estimation of a depth map. As our input is a single portrait picture, we constraint our objects to humans first and utilise skin detection. A further extension alleviates this. With auxiliary user input we further refine our depth map estimate to a full-fledged foreground–background segmentation. This enables the computation of the actual blurred image at the very end of our pipeline.