Shape from texture without boundaries

Research output: Contribution to journalArticle

Abstract

We describe a shape from texture method that constructs an estimate of surface geometry using only the deformation of individual texture elements. Our method does not need to use either the boundary of the observed surface or any assumption about the overall distribution of elements.The method assumes that surface texture elements are drawn from a number of different types, each of fixed shape. Neither the shape of the elements nor the number of types need be known in advance. We show that, with this assumption and assuming a generic, scaled orthographic view and texture, each type of texture element can be reconstructed in a frontal coordinate system from image instances. Interest-point methods supply a method of simultaneously obtaining instances of each texture element automatically and defining each type of element. Furthermore, image instances that have been marked in error can be identified and ignored using the Expectation-Maximization algorithm. A further EM procedure yields a surface reconstruction and a relative irradiance map from the data. We provide numerous examples of reconstructions for images of real scenes, show a comparison between our reconstruction and range maps, and demonstrate that the reconstructions display geometric and irradiance phenomena that can be observed in the original image.

Original languageEnglish (US)
Pages (from-to)71-91
Number of pages21
JournalInternational Journal of Computer Vision
Volume67
Issue number1
DOIs
StatePublished - Apr 1 2006
Externally publishedYes

Fingerprint

Textures
Surface reconstruction
Geometry

Keywords

  • Auto-calibration
  • Computer vision
  • Interest point methods
  • Shape from texture
  • Structure from motion
  • Surface fitting
  • Texture

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Shape from texture without boundaries. / Lobay, Anthony; Forsyth, David Alexander.

In: International Journal of Computer Vision, Vol. 67, No. 1, 01.04.2006, p. 71-91.

Research output: Contribution to journalArticle

@article{121d719eafe547c795d98b9d1451fed1,
title = "Shape from texture without boundaries",
abstract = "We describe a shape from texture method that constructs an estimate of surface geometry using only the deformation of individual texture elements. Our method does not need to use either the boundary of the observed surface or any assumption about the overall distribution of elements.The method assumes that surface texture elements are drawn from a number of different types, each of fixed shape. Neither the shape of the elements nor the number of types need be known in advance. We show that, with this assumption and assuming a generic, scaled orthographic view and texture, each type of texture element can be reconstructed in a frontal coordinate system from image instances. Interest-point methods supply a method of simultaneously obtaining instances of each texture element automatically and defining each type of element. Furthermore, image instances that have been marked in error can be identified and ignored using the Expectation-Maximization algorithm. A further EM procedure yields a surface reconstruction and a relative irradiance map from the data. We provide numerous examples of reconstructions for images of real scenes, show a comparison between our reconstruction and range maps, and demonstrate that the reconstructions display geometric and irradiance phenomena that can be observed in the original image.",
keywords = "Auto-calibration, Computer vision, Interest point methods, Shape from texture, Structure from motion, Surface fitting, Texture",
author = "Anthony Lobay and Forsyth, {David Alexander}",
year = "2006",
month = "4",
day = "1",
doi = "10.1007/s11263-006-4068-8",
language = "English (US)",
volume = "67",
pages = "71--91",
journal = "International Journal of Computer Vision",
issn = "0920-5691",
publisher = "Springer Netherlands",
number = "1",

}

TY - JOUR

T1 - Shape from texture without boundaries

AU - Lobay, Anthony

AU - Forsyth, David Alexander

PY - 2006/4/1

Y1 - 2006/4/1

N2 - We describe a shape from texture method that constructs an estimate of surface geometry using only the deformation of individual texture elements. Our method does not need to use either the boundary of the observed surface or any assumption about the overall distribution of elements.The method assumes that surface texture elements are drawn from a number of different types, each of fixed shape. Neither the shape of the elements nor the number of types need be known in advance. We show that, with this assumption and assuming a generic, scaled orthographic view and texture, each type of texture element can be reconstructed in a frontal coordinate system from image instances. Interest-point methods supply a method of simultaneously obtaining instances of each texture element automatically and defining each type of element. Furthermore, image instances that have been marked in error can be identified and ignored using the Expectation-Maximization algorithm. A further EM procedure yields a surface reconstruction and a relative irradiance map from the data. We provide numerous examples of reconstructions for images of real scenes, show a comparison between our reconstruction and range maps, and demonstrate that the reconstructions display geometric and irradiance phenomena that can be observed in the original image.

AB - We describe a shape from texture method that constructs an estimate of surface geometry using only the deformation of individual texture elements. Our method does not need to use either the boundary of the observed surface or any assumption about the overall distribution of elements.The method assumes that surface texture elements are drawn from a number of different types, each of fixed shape. Neither the shape of the elements nor the number of types need be known in advance. We show that, with this assumption and assuming a generic, scaled orthographic view and texture, each type of texture element can be reconstructed in a frontal coordinate system from image instances. Interest-point methods supply a method of simultaneously obtaining instances of each texture element automatically and defining each type of element. Furthermore, image instances that have been marked in error can be identified and ignored using the Expectation-Maximization algorithm. A further EM procedure yields a surface reconstruction and a relative irradiance map from the data. We provide numerous examples of reconstructions for images of real scenes, show a comparison between our reconstruction and range maps, and demonstrate that the reconstructions display geometric and irradiance phenomena that can be observed in the original image.

KW - Auto-calibration

KW - Computer vision

KW - Interest point methods

KW - Shape from texture

KW - Structure from motion

KW - Surface fitting

KW - Texture

UR - http://www.scopus.com/inward/record.url?scp=33644537054&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33644537054&partnerID=8YFLogxK

U2 - 10.1007/s11263-006-4068-8

DO - 10.1007/s11263-006-4068-8

M3 - Article

AN - SCOPUS:33644537054

VL - 67

SP - 71

EP - 91

JO - International Journal of Computer Vision

JF - International Journal of Computer Vision

SN - 0920-5691

IS - 1

ER -