Issue No. 04 - April (2002 vol. 24)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/34.993560
<p>This paper studies the recovery of shape from texture under perspective projection. We regard <it>Shape from Texture</it> as a statistical estimation problem, the texture being the realization of a stochastic process. We introduce <it>warplets</it>, which generalize wavelets over the 2D affine group. At fine scales, the warpogram of the image obeys a transport equation, called <it>Texture Gradient Equation</it>. In order to recover the 3D shape of the surface, one must estimate the <it>deformation gradient</it>, which measures metric changes in the image. This is made possible by imposing a notion of homogeneity for the original texture, according to which the deformation gradient is equal to the velocity of the Texture Gradient Equation. By measuring the warplet transform of the image at different scales, we obtain a deformation gradient estimator.</p>
shape from texture, texture gradient, warplets, wavelets
S. Mallat and M. Clerc, "The Texture Gradient Equation for Recovering Shape from Texture," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 24, no. , pp. 536-549, 2002.