Combining cues: Shape from shading and texture

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We demonstrate a method for reconstructing the shape of a deformed surface from a single view. After decomposing an image into irradiance and albedo components, we combine normal cues from shading and texture to produce a field of unambiguous normals. Using these normals, we reconstruct the 3D geometry. Our method works in two regimes: either requiring the frontal appearance of the texture or building it automatically from a series of images of the deforming texture. We can recover geometry with errors below four percent of object size on arbitrary textures, and estimate specific geometric parameters using a custom texture even more accurately.

Original languageEnglish (US)
Title of host publicationProceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006
Pages1809-1816
Number of pages8
DOIs
StatePublished - Dec 22 2006
Event2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006 - New York, NY, United States
Duration: Jun 17 2006Jun 22 2006

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume2
ISSN (Print)1063-6919

Other

Other2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006
CountryUnited States
CityNew York, NY
Period6/17/066/22/06

Fingerprint

Textures
Geometry

Keywords

  • 3D reconstruction
  • Deformable models
  • Shape-from-shading
  • Shape-from-texture
  • Surface tracking

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Cite this

White, R., & Forsyth, D. A. (2006). Combining cues: Shape from shading and texture. In Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006 (pp. 1809-1816). [1640973] (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 2). https://doi.org/10.1109/CVPR.2006.79

Combining cues : Shape from shading and texture. / White, Ryan; Forsyth, David Alexander.

Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006. 2006. p. 1809-1816 1640973 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 2).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

White, R & Forsyth, DA 2006, Combining cues: Shape from shading and texture. in Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006., 1640973, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 1809-1816, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006, New York, NY, United States, 6/17/06. https://doi.org/10.1109/CVPR.2006.79
White R, Forsyth DA. Combining cues: Shape from shading and texture. In Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006. 2006. p. 1809-1816. 1640973. (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). https://doi.org/10.1109/CVPR.2006.79
White, Ryan ; Forsyth, David Alexander. / Combining cues : Shape from shading and texture. Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006. 2006. pp. 1809-1816 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).
@inproceedings{d4caa551727b4288918b92331b00c88f,
title = "Combining cues: Shape from shading and texture",
abstract = "We demonstrate a method for reconstructing the shape of a deformed surface from a single view. After decomposing an image into irradiance and albedo components, we combine normal cues from shading and texture to produce a field of unambiguous normals. Using these normals, we reconstruct the 3D geometry. Our method works in two regimes: either requiring the frontal appearance of the texture or building it automatically from a series of images of the deforming texture. We can recover geometry with errors below four percent of object size on arbitrary textures, and estimate specific geometric parameters using a custom texture even more accurately.",
keywords = "3D reconstruction, Deformable models, Shape-from-shading, Shape-from-texture, Surface tracking",
author = "Ryan White and Forsyth, {David Alexander}",
year = "2006",
month = "12",
day = "22",
doi = "10.1109/CVPR.2006.79",
language = "English (US)",
isbn = "0769525970",
series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
pages = "1809--1816",
booktitle = "Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006",

}

TY - GEN

T1 - Combining cues

T2 - Shape from shading and texture

AU - White, Ryan

AU - Forsyth, David Alexander

PY - 2006/12/22

Y1 - 2006/12/22

N2 - We demonstrate a method for reconstructing the shape of a deformed surface from a single view. After decomposing an image into irradiance and albedo components, we combine normal cues from shading and texture to produce a field of unambiguous normals. Using these normals, we reconstruct the 3D geometry. Our method works in two regimes: either requiring the frontal appearance of the texture or building it automatically from a series of images of the deforming texture. We can recover geometry with errors below four percent of object size on arbitrary textures, and estimate specific geometric parameters using a custom texture even more accurately.

AB - We demonstrate a method for reconstructing the shape of a deformed surface from a single view. After decomposing an image into irradiance and albedo components, we combine normal cues from shading and texture to produce a field of unambiguous normals. Using these normals, we reconstruct the 3D geometry. Our method works in two regimes: either requiring the frontal appearance of the texture or building it automatically from a series of images of the deforming texture. We can recover geometry with errors below four percent of object size on arbitrary textures, and estimate specific geometric parameters using a custom texture even more accurately.

KW - 3D reconstruction

KW - Deformable models

KW - Shape-from-shading

KW - Shape-from-texture

KW - Surface tracking

UR - http://www.scopus.com/inward/record.url?scp=33845581708&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33845581708&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2006.79

DO - 10.1109/CVPR.2006.79

M3 - Conference contribution

AN - SCOPUS:33845581708

SN - 0769525970

SN - 9780769525976

T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SP - 1809

EP - 1816

BT - Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006

ER -