Shape from texture using locally scaled point processes

• Verfasst von: Didden, Eva-Maria [VerfasserIn]
• Verfasst von: Thorarinsdottir, Thordis [VerfasserIn]
• Verfasst von: Schnörr, Christoph [VerfasserIn]
• Titel: Shape from texture using locally scaled point processes
• Verf.angabe: Eva-Maria Didden, Thordis Thorarinsdottir, Alex Lenkoski and Christoph Schnörr
• Umfang: 10 S.
• Fussnoten: Gesehen am 24.05.2018
• Titel Quelle: Enthalten in: Image, analysis & stereology
• Jahr Quelle: 2015
• Band/Heft Quelle: 34(2015), 3, S. 161-170
• ISSN Quelle: 1854-5165
• DOI: doi:10.5566/ias.1078
• Datenträger: Online-Ressource
• Sprache: eng
• K10plus-PPN: 1575483491

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.