SHAPE FROM TEXTURE USING LOCALLY SCALED POINT PROCESSES

Eva-Maria Didden, Thordis Thorarinsdottir, Alex Lenkoski, Christoph Schnörr

Abstract

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.


Keywords
3D scenes; convex texture elements; locally scaled point processes; near regular texture; perspective scaling; shape analysis

Full Text:

PDF


DOI: 10.5566/ias.1078

Image Analysis & Stereology
EISSN 1854-5165 (Electronic version)
ISSN 1580-3139 (Printed version)