Publications

Detecting Photoshopped Images by Scripting Photoshop

International Conference on Computer Vision (ICCV'19)

Publication date: October 31, 2019

Sheng-Yu Wang, Oliver Wang, Andrew Owens, Richard Zhang, Alexei A. Efros

Most malicious photo manipulations are created using standard image editing tools, such as Adobe Photoshop. We present a method for detecting one very popular Photoshop manipulation -- image warping applied to human faces -- using a model trained entirely using fake images that were automatically generated by scripting Photoshop itself. We show that our model outperforms humans at the task of recognizing manipulated images, can predict the specific location of edits, and in some cases can be used to "undo" a manipulation to reconstruct the original, unedited image. We demonstrate that the system can be successfully applied to real, artist-created image manipulations.

Learn More