Scene Completion Using Millions of Photographs



What can you do with a million images? In this paper we present a new image completion algorithm powered by a huge database of photographs gathered from the Web. The algorithm patches up holes in images by finding similar image regions in the database that are not only seamless but also semantically valid. Our chief insight is that while the space of images is effectively infinite, the space of semantically differentiable scenes is actually not that large. For many image completion tasks we are able to find similar scenes which contain image fragments that will convincingly complete the image. Our algorithm is entirely data-driven, requiring no annotations or labelling by the user. Unlike existing image completion methods, our algorithm can generate a diverse set of image completions and we allow users to select among them. We demonstrate the superiority of our algorithm over existing image completion approaches.

paper thumbnail


SIGGRAPH paper. (pdf, 11MB)

Communications of the ACM paper. (pdf, 15MB) with Technical Perspective by Marc Levoy.


.zip file (ppt + movies), 90MB


James Hays, Alexei A. Efros. Scene Completion Using Millions of Photographs. ACM Transactions on Graphics (SIGGRAPH 2007). August 2007, vol. 26, No. 3.


  test set thumbnails


Image Downloading Code

Code for downloading Flickr images.


I'm aware of two class projects which implemented Scene Completion with smaller data sets. The results are very interesting.
I also had my Computational Photography Class implement Scene Completion, with scene matches from the larger im2gps database. The results are significantly better than the original SIGGRAPH project in some cases.


This research is supported in part by: