SHAPE FROM TEXTURE USING LOCALLY SCALED POINT PROCESSES
DOI:
https://doi.org/10.5566/ias.1078Keywords:
3D scenes, convex texture elements, locally scaled point processes, near regular texture, perspective scaling, shape analysisAbstract
Shape from texture refers to the extraction of 3D information from 2D images with irregular texture. This paper introduces a statistical framework to learn shape from texture where convex texture elements in a 2D image are represented through a point process. In a first step, the 2D image is preprocessed to generate a probability map corresponding to an estimate of the unnormalized intensity of the latent point process underlying the texture elements. The latent point process is subsequently inferred from the probability map in a non-parametric, model free manner. Finally, the 3D information is extracted from the point pattern by applying a locally scaled point process model where the local scaling function represents the deformation caused by the projection of a 3D surface onto a 2D image.
References
Blake, A., Marinos, C. (1990): Shape from texture: Estimation, isotropy and moments. Artif. Intellig. 45, 323–380.
Blostein, D., Ahuja, N. (1989): Shape from texture: Integrating texture-element extraction and surface estimation. IEEE Trans. Patt. Anal. Mach. Intell. PAMI-11, 1233–1251.
Canny, J. (1986): A computational approach to edge detection. IEEE Trans. Patt. Anal. Mach. Intell. PAMI-8, 679–698.
Clerc, M., Mallat, S. (2002): The texture gradient equation for recovering shape from texture. IEEE Trans. Patt. Anal. Mach. Intell. 24(4), 536–549.
Forsyth, D. (2006): Shape from texture without boundaries. Int. J. Comp. Vision 67(1), 71–91.
Gibson, J. (1950): The perception of the visual world. Houghton Mifflin, Boston, MA.
Hahn, U., Jensen, E.V., van Lieshout, M.C., Nielsen, L. (2003): Inhomogenous spatial point processes by location-dependent scaling. Adv. Appl. Prob. (SGSA) 35, 319– 336.
Hartley, R., Zisserman, A. (2000): Multiple view geometry in computer vision. Cambridge Univ. Press.
Kanatani, K. (1989): Shape from texture: General principle. Artif. Intell. 38, 1–48.
Lafarge, F., Gimel’Farb, G., Descombes, X. (2010): Geometric feature extraction by a multi-marked point process. IEEE Trans. Patt. Anal. Mach. Intell. 32(9), 1597–1609.
Liu, Y., Hel-Or, H., Kaplan, C., Van Gool, L. (2009): Computational symmetry in computer vision and computer graphics. Found. Trends Comp. Graphics and Vision 5(1-2), 1–195.
Loh, A., Hartley, R. (2005): Shape from non-homogeneous, non-stationary, anisotropic, perspective texture. In: Proc. BMVC. pp. 69–78.
Malik, J., Rosenholtz, R. (1997): Computing local surface orientation and shape from texture for curved surfaces. Int. J. Comp. Vision 23(2), 149–168.
Møller, J. (2010): Spatial point patterns: Parametric Methods. In: Gelfand, A.E., Diggle, P.J., Fuentes, M., Guttorp, P. (eds.) Handbook of Spatial Statistics. CRC Press, Boca Raton, FL.
Møller, J., Waagepetersen, R.P. (2004): Statistical Inference and Simulation for Spatial Point Processes. Chapman & Hall/CRC, Boca Raton, FL.
Pele, O., Werman, W. (2009): Fast and robust earth mover’s distances. In: Proc. Int. Conf. Comp. Vision (ICCV).
Prokesova, M., Hahn, U., Jensen, E.B.V. (2006): Statistics for locally scaled point processes. In: Baddeley, A., Gregori, P.,
Mateu, J., Stoica, R., Stoyan, D. (eds.) Case Studies in Spatial Point Process Modelling. vol. 185, pp. 99–123. Springer, New York.
Rajala, T., Penttinen, A. (2012): Bayesian analysis of a Gibbs hard-core point pattern model with varying repulsion range. Comp. Stat. Data Anal. in press.
Stevens, K.A. (1980): Surface perception from local analysis of texture and contour. Tech. Rep. AI-TR 512, MIT Technical Report, Artificial Intelligence Laboratory.
Tuceryan, M., Jain, A.K. (1998): Texture analysis. In: Chen, C.H., Pau, L.F., Wang, P.S.P. (eds.) Handbook of Pattern Recognition and Computer Vision (2nd edition). pp. 207–248. World Scientific, Singapore.
Witkin, A.P. (1981): Recovering surface shape and orientation from texture. Artif. Intellig. 17, 17–45.
