Recovering shape and irradiance maps from rich dense texton fields

Anthony Lobay, D. A. Forsyth

Research output: Contribution to journalConference article

Abstract

We describe a method that recovers an estimate of surface shape and of the irradiance field for a textured surface. The method assumes the surface is viewed in scaled orthography, and we demonstrate the appropriateness of this assumption. Our method uses interest points to obtain the locations of putative texton instances, clusters the textons into types, and then uses an autocalibration method to recover the frontal appearance of each texton model. This yields (a) a dense set of normal estimates, each up to a two-fold ambiguity (b) a dense set of irradiance estimates and (c) whether each instance is, in fact, an instance of the relevant texton. Because we are able to obtain a very large number of instances of a large number of different textons, this information is obtained at sites very closely spaced in the image. As a result, we need only a simple smoothness constraint to reconstruct a surface model, using EM to resolve the normal ambiguity. We show results on images of real scenes, comparing our reconstructions with those obtained using other methods and demonstrating the accuracy of both the recovered shape and the irradiance estimate.

Original languageEnglish (US)
Pages (from-to)I400-I406
JournalProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume1
StatePublished - Oct 19 2004
Externally publishedYes
EventProceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2004 - Washington, DC, United States
Duration: Jun 27 2004Jul 2 2004

Keywords

  • Computer vision
  • Point features
  • Shading maps
  • Shape from texture
  • Surface fitting
  • Textons
  • Texture

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Recovering shape and irradiance maps from rich dense texton fields. / Lobay, Anthony; Forsyth, D. A.

In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. 1, 19.10.2004, p. I400-I406.

Research output: Contribution to journalConference article

@article{d692e1e7f84d491a993049feb3fddbcc,
title = "Recovering shape and irradiance maps from rich dense texton fields",
abstract = "We describe a method that recovers an estimate of surface shape and of the irradiance field for a textured surface. The method assumes the surface is viewed in scaled orthography, and we demonstrate the appropriateness of this assumption. Our method uses interest points to obtain the locations of putative texton instances, clusters the textons into types, and then uses an autocalibration method to recover the frontal appearance of each texton model. This yields (a) a dense set of normal estimates, each up to a two-fold ambiguity (b) a dense set of irradiance estimates and (c) whether each instance is, in fact, an instance of the relevant texton. Because we are able to obtain a very large number of instances of a large number of different textons, this information is obtained at sites very closely spaced in the image. As a result, we need only a simple smoothness constraint to reconstruct a surface model, using EM to resolve the normal ambiguity. We show results on images of real scenes, comparing our reconstructions with those obtained using other methods and demonstrating the accuracy of both the recovered shape and the irradiance estimate.",
keywords = "Computer vision, Point features, Shading maps, Shape from texture, Surface fitting, Textons, Texture",
author = "Anthony Lobay and Forsyth, {D. A.}",
year = "2004",
month = "10",
day = "19",
language = "English (US)",
volume = "1",
pages = "I400--I406",
journal = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
issn = "1063-6919",
publisher = "IEEE Computer Society",

}

TY - JOUR

T1 - Recovering shape and irradiance maps from rich dense texton fields

AU - Lobay, Anthony

AU - Forsyth, D. A.

PY - 2004/10/19

Y1 - 2004/10/19

N2 - We describe a method that recovers an estimate of surface shape and of the irradiance field for a textured surface. The method assumes the surface is viewed in scaled orthography, and we demonstrate the appropriateness of this assumption. Our method uses interest points to obtain the locations of putative texton instances, clusters the textons into types, and then uses an autocalibration method to recover the frontal appearance of each texton model. This yields (a) a dense set of normal estimates, each up to a two-fold ambiguity (b) a dense set of irradiance estimates and (c) whether each instance is, in fact, an instance of the relevant texton. Because we are able to obtain a very large number of instances of a large number of different textons, this information is obtained at sites very closely spaced in the image. As a result, we need only a simple smoothness constraint to reconstruct a surface model, using EM to resolve the normal ambiguity. We show results on images of real scenes, comparing our reconstructions with those obtained using other methods and demonstrating the accuracy of both the recovered shape and the irradiance estimate.

AB - We describe a method that recovers an estimate of surface shape and of the irradiance field for a textured surface. The method assumes the surface is viewed in scaled orthography, and we demonstrate the appropriateness of this assumption. Our method uses interest points to obtain the locations of putative texton instances, clusters the textons into types, and then uses an autocalibration method to recover the frontal appearance of each texton model. This yields (a) a dense set of normal estimates, each up to a two-fold ambiguity (b) a dense set of irradiance estimates and (c) whether each instance is, in fact, an instance of the relevant texton. Because we are able to obtain a very large number of instances of a large number of different textons, this information is obtained at sites very closely spaced in the image. As a result, we need only a simple smoothness constraint to reconstruct a surface model, using EM to resolve the normal ambiguity. We show results on images of real scenes, comparing our reconstructions with those obtained using other methods and demonstrating the accuracy of both the recovered shape and the irradiance estimate.

KW - Computer vision

KW - Point features

KW - Shading maps

KW - Shape from texture

KW - Surface fitting

KW - Textons

KW - Texture

UR - http://www.scopus.com/inward/record.url?scp=5044228744&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=5044228744&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:5044228744

VL - 1

SP - I400-I406

JO - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

JF - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SN - 1063-6919

ER -