Perspective-aware Manipulation of Portrait Photos

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 Similar Projects

Use your own photo.

Upload photo Down for maintenance

Try one of our pre-calculated examples

1 2 3 4 5

Watch the video

CMDP dataset Inputs from the web Expressive faces Mannequin

	author = {Fried, Ohad and Shechtman, Eli and Goldman, Dan B. and Finkelstein, Adam},
	title = {Perspective-aware Manipulation of Portrait Photos},
	journal = {ACM Trans. Graph.},
	issue_date = {July 2016},
	volume = {35},
	number = {4},
	month = jul,
	year = {2016},
	issn = {0730-0301},
	pages = {128:1--128:10},
	articleno = {128},
	numpages = {10},
	url = {},
	doi = {10.1145/2897824.2925933},
	acmid = {2925933},
	publisher = {ACM},
	address = {New York, NY, USA},
	keywords = {faces, image enhancement, perspective, portraits},