SHAPE FROM TEXTURE USING LOCALLY SCALED POINT PROCESSES
Image Analysis & Stereology · 2015
DOI: 10.5566/ias.1078 ↗Kurz gefasst
Fachartikel in der Zeitschrift Image Analysis & Stereology, 2015. Verfasst von Eva-Maria Didden und 3 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref).
Abstract (Originalsprache)
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.
Zitieren
APA
Didden, E., Thorarinsdottir, T., Lenkoski, A., & Schnörr, C. (2015). SHAPE FROM TEXTURE USING LOCALLY SCALED POINT PROCESSES. Image Analysis & Stereology. https://doi.org/10.5566/ias.1078
Vancouver
Didden E, Thorarinsdottir T, Lenkoski A, Schnörr C. SHAPE FROM TEXTURE USING LOCALLY SCALED POINT PROCESSES. Image Analysis & Stereology. 2015. doi:10.5566/ias.1078
BibTeX
@article{Didden2015,
author = {Didden, Eva-Maria and Thorarinsdottir, Thordis and Lenkoski, Alex and Schnörr, Christoph},
title = {SHAPE FROM TEXTURE USING LOCALLY SCALED POINT PROCESSES},
journal = {Image Analysis & Stereology},
year = {2015},
doi = {10.5566/ias.1078}
}
EUVIMED