Photo Clip Art (original) (raw)

Live demo

People

Abstract

Graphical User Interface
Snapshot of our interface

We present a system for inserting new objects into existing photographs by querying a vast image-based object library, precomputed using a publicly available Internet object database. The central goal is to shield the user from all of the arduous tasks typically involved in image compositing. The user is only asked to do two simple things: 1) pick a 3D location in the scene to place a new object; 2) select an object to insert using a hierarchical menu. We pose the problem of object insertion as a data-driven, 3D-based, context-sensitive object retrieval task. Instead of trying to manipulate the object to change its orientation, color distribution, etc. to fit the new image, we simply retrieve an object of a specified class that has all the required properties (camera pose, lighting, resolution, etc) from our large object library. We present new automatic algorithms for improving object segmentation and blending, estimating true 3D object size and orientation, and estimating scene lighting conditions. We also present an intuitive user interface that makes object insertion fast and simple even for the artistically challenged.

Citation

Talk

Download the slides from the talk given at SIGGRAPH 2007 in the following formats:

Video

Photo Clip Art from Jean-Francois Lalonde on Vimeo.

Snapshot for movie[MPEG-4, 720x480 NTSC, 37.9MB]

Results

View additional results here. Click on the images for high resolution versions.

Media coverage

This project has been getting quite a bit a media coverage. Here's a summary of the most notable places where Photo Clip Art was mentioned (if I've missed some, please let me know).

Acknowledgements and Funding

This work would not have been possible without the efforts of Bryan Russell, Antonio Torralba and the rest of the LabelMe team in designing the labeling tool and maintaining the database.

This research is supported by: