Abstract | ||
---|---|---|
When we take a picture through transparent glass the image we obtain is often a linear superposition of two images: the image of the scene beyond the glass plus the image of the scene reflected by the glass. Decomposing the single input image into two images is a massively ill-posed problem: in the absence of additional knowledge about the scene being viewed there are an infinite number of valid decompositions. In this paper we focus on an easier problem: user assisted separation in which the user interactively labels a small number of gradients as belonging to one of the layers. Even given labels on part of the gradients, the problem is still ill-posed and additional prior knowledge is needed. Following recent results on the statistics of natural images we use a sparsity prior over derivative filters. This sparsity prior is optimized using the terative reweighted least squares (IRLS) approach. Our results show that using a prior derived from the statistics of natural images gives a far superior performance compared to a Gaussian prior and it enables good separations from a modest number of labeled gradients. |
Year | DOI | Venue |
---|---|---|
2007 | 10.1109/TPAMI.2007.1106 | ECCV |
Keywords | Field | DocType |
transparency,iterative methods,reflection,computer graphics,lenses,glass,linear superposition,painting,image processing | Small number,Computer vision,Superposition principle,Pattern recognition,Computer science,Artificial intelligence,Machine learning | Journal |
Volume | Issue | ISSN |
29 | 9 | 0162-8828 |
Citations | PageRank | References |
110 | 8.68 | 15 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Anat Levin | 1 | 3578 | 212.90 |
Yair Weiss | 2 | 10240 | 834.60 |