Perspective-aware Manipulation of Portrait Photos

Ohad Fried

Princeton

Eli Shechtman

Adobe Research

Dan Goldman

Adobe Research

Adam Finkelstein

Princeton

Ian Sachs

Adobe Research

We introduce a method to modify the apparent relative pose and distance between camera and subject given a single portrait photo. Our approach fits a full perspective camera and a parametric 3D head model to the portrait, and then builds a 2D warp in the image plane to approximate the effect of a desired change in 3D. We show that this model is capable of correcting objectionable artifacts such as the large noses sometimes seen in “selfies,” or to deliberately bring a distant camera closer to the subject. This framework can also be used to re-pose the subject, as well as to create stereo pairs from an input portrait. We show convincing results on both an existing dataset as well as a new dataset we captured to validate our method.

Princeton project page

Media coverage:
[Gizmodo] [Motherboard] [Lonely Planet] [Forbes] [CNN] [FastCompany] [CACM] [DPReview] [DailyMail] [Yahoo Tech][Digital Trends] [Gizmag] [Wired DE] [Spiegel] [PetaPixel] [TOI] [Science 2.0] [cnet] [NJ] [DIYPhotography] [designboom][Fstoppers] [Inverse] [Princeton] [ICSJ]

Ian demos the technology on mobile.

Project Publications

Perspective-aware Manipulation of Portrait Photos

Fried, O., Shechtman, E., Goldman, D., Finkelstein, A. (Jul. 24, 2016)
ACM Transactions on Graphics (Proc. SIGGRAPH'16)