CSDL Home IEEE Transactions on Pattern Analysis & Machine Intelligence 2008 vol.30 Issue No.03 - March

Subscribe

Issue No.03 - March (2008 vol.30)

pp: 518-531

ABSTRACT

Defocus can be modeled as a diffusion process and represented mathematically using the heat equation, where image blur corresponds to the diffusion of heat. This analogy can be extended to non-planar scenes by allowing a space-varying diffusion coefficient. The inverse problem of reconstructing 3-D structure from blurred images corresponds to an “inverse diffusion” that is notoriously ill-posed. We show how to bypass this problem by using the notion of relative blur. Given two images, within each neighborhood, the amount of diffusion necessary to transform the sharper image into the blurrier one depends on the depth of the scene. This can be used to devise a global algorithm to estimate the depth profile of the scene without recovering the deblurred image, using only forward diffusion.

INDEX TERMS

Shape, Reconstruction, Depth cues, Gradient methods, Iterative methods, Partial differential equations, Inverse problems, Sharpening and Deblurring

CITATION

Paolo Favaro, Stefano Soatto, Martin Burger, Stanley J. Osher, "Shape from Defocus via Diffusion",

*IEEE Transactions on Pattern Analysis & Machine Intelligence*, vol.30, no. 3, pp. 518-531, March 2008, doi:10.1109/TPAMI.2007.1175REFERENCES