Inserting Synthetic Objects Into A Photo

Rendering Synthetic Objects into Legacy Photographs from Kevin Karsch on Vimeo.

We will soon need stronger mechanisms to guarantee that a photo has not been altered. Not only is it relatively simple to digitally manipulate a photo today in Photoshop, but even more powerful algorithms are coming out to digitally manipulate a photo: e.g. the capability to insert an object into an existing photo so that one cannot tell that it was added.

Supplementary material video for our 2011 SIGGRAPH Asia paper (see the project page here: 3D objects are rendered using LuxRender (

Authors: Kevin Karsch, Varsha Hedau, David Forsyth, Derek Hoiem

Abstract: We propose a method to realistically insert synthetic objects into existing photographs without requiring access to the scene or any additional scene measurements. With a single image and a small amount of annotation, our method creates a physical model of the scene that is suitable for realistically rendering synthetic objects with diffuse, specular, and even glowing materials while accounting for lighting interactions between the objects and the scene. We demonstrate in a user study that synthetic images produced by our method are confusable with real scenes, even for people who believe they are good at telling the difference. Further, our study shows that our method is competitive with other insertion methods while requiring less scene information. We also collected new illumination and reflectance datasets; renderings produced by our system compare well to ground truth. Our system has applications in the movie and gaming industry, as well as home decorating and user content creation, among others.

via laughingsquid