Data-driven Suggestions for Portrait Posing (Best Demo Voted by Attendees)

This work introduces an easy-to-use creativity support tool for portrait posing, which is an important but challenging problem in portrait photography. While it is well known that a collection of sample poses is a source of inspiration, manual browsing is the only option to identify a desired pose from a possibly large collection of poses. With our tool, a photographer is able to easily retrieve desired reference poses as guidance or stimulate creativity. We show how our data-driven suggestions can be effectively used to either refine the current pose of a subject or explore new poses. Our tool greatly helps unskilled photographers create aesthetically pleasing portraits with diversity. Our work takes the first step of using consumer-level depth sensors towards more intelligent cameras for computational photography.

Hongbo Fu
City University of Hong Kong

Xiaoguang Han
City University of Hong Kong

Quoc Huy Phan
City University of Hong Kong