Rendering Synthetic Objects into Legacy Photographs

TL;DR

This paper presents a method for inserting synthetic objects into existing photographs realistically, using minimal scene information, and demonstrates its effectiveness through user studies and dataset comparisons.

Contribution

The method allows realistic insertion of synthetic objects into photographs with limited scene data, accounting for complex lighting effects, and introduces new datasets for illumination and reflectance.

Findings

Synthetic images are often indistinguishable from real scenes in user studies.

The method performs competitively with existing techniques while requiring less scene information.

Renderings match ground truth data well in new illumination and reflectance datasets.

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.