Perspective-aware Manipulation of Portrait Photos

ACM Transactions on Graphics (Proc. SIGGRAPH), July 2016

Ohad Fried, Eli Shechtman,
Dan B Goldman, Adam Finkelstein

Comparing real photos taken with a far (a) or near (d) camera, one can observe the subtle effect of perspective on portrait photos. We simulate this effect by warping (a) → (c) to match the apparent distance of (d); and also (d) → (b) to match the distance of (a). These warps are guided by an underlying 3D head model.

This paper introduces 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.

Paper-preprint (5MB PDF)
Video (93MB MP4)
Demo

Ohad Fried, Eli Shechtman, Dan B Goldman, and Adam Finkelstein.
"Perspective-aware Manipulation of Portrait Photos."
ACM Transactions on Graphics (Proc. SIGGRAPH), July 2016.

@article{Fried:2016:PMO,
   author = "Ohad Fried and Eli Shechtman and Dan B Goldman and Adam Finkelstein",
   title = "Perspective-aware Manipulation of Portrait Photos",
   journal = "ACM Transactions on Graphics (Proc. SIGGRAPH)",
   year = "2016",
   month = jul
}