Learning how to inpaint from global image statistics

Anat Levin*, Assaf Zomet, Yair Weiss

*Corresponding author for this work

Research output: Contribution to conferencePaperpeer-review

293 Scopus citations


Inpainting is the problem of filling-in holes in images. Considerable progress has been made by techniques that use the immediate boundary of the hole and some prior information on images to solve this problem. These algorithms successfully solve the local inpainting problem but they must, by definition, give the same completion to any two holes that have the same boundary, even when the rest of the image is vastly different. In this paper we address a different, more global inpainting problem. How can we use the rest of the image in order to learn how to inpaint? We approach this problem from the context of statistical learning. Given a training image we build an exponential family distribution over images that is based on the histograms of local features. We then use this image specific distribution to inpaint the hole by finding the most probable image given the boundary and the distribution. The optimization is done using loopy belief propagation. We show that our method can successfully complete holes while taking into account the specific image statistics. In particular it can give vastly different completions even when the local neighborhoods are identical.

Original languageAmerican English
Number of pages8
StatePublished - 2003
EventProceedings: Ninth IEEE International Conference on Computer Vision - Nice, France
Duration: 13 Oct 200316 Oct 2003


ConferenceProceedings: Ninth IEEE International Conference on Computer Vision


Dive into the research topics of 'Learning how to inpaint from global image statistics'. Together they form a unique fingerprint.

Cite this