Non-parametric filtering for geometric detail extraction and material representation

Zicheng Liao, Jason Rock, Yang Wang, David Alexander Forsyth

Research output: Contribution to journalConference article

Abstract

Geometric detail is a universal phenomenon in real world objects. It is an important component in object modeling, but not accounted for in current intrinsic image works. In this work, we explore using a non-parametric method to separate geometric detail from intrinsic image components. We further decompose an image as albedo * (coarse-scale shading + shading detail). Our decomposition offers quantitative improvement in albedo recovery and material classification. Our method also enables interesting image editing activities, including bump removal, geometric detail smoothing/enhancement and material transfer.

Original languageEnglish (US)
Article number6618973
Pages (from-to)963-970
Number of pages8
JournalProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
DOIs
StatePublished - Nov 15 2013
Event26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2013 - Portland, OR, United States
Duration: Jun 23 2013Jun 28 2013

Fingerprint

Decomposition
Recovery

Keywords

  • Geometric detail
  • intrinsic image decomposition
  • material representation

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Cite this

@article{6c97e11a7a4e4f9aad47fdce35c6c4ed,
title = "Non-parametric filtering for geometric detail extraction and material representation",
abstract = "Geometric detail is a universal phenomenon in real world objects. It is an important component in object modeling, but not accounted for in current intrinsic image works. In this work, we explore using a non-parametric method to separate geometric detail from intrinsic image components. We further decompose an image as albedo * (coarse-scale shading + shading detail). Our decomposition offers quantitative improvement in albedo recovery and material classification. Our method also enables interesting image editing activities, including bump removal, geometric detail smoothing/enhancement and material transfer.",
keywords = "Geometric detail, intrinsic image decomposition, material representation",
author = "Zicheng Liao and Jason Rock and Yang Wang and Forsyth, {David Alexander}",
year = "2013",
month = "11",
day = "15",
doi = "10.1109/CVPR.2013.129",
language = "English (US)",
pages = "963--970",
journal = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
issn = "1063-6919",
publisher = "IEEE Computer Society",

}

TY - JOUR

T1 - Non-parametric filtering for geometric detail extraction and material representation

AU - Liao, Zicheng

AU - Rock, Jason

AU - Wang, Yang

AU - Forsyth, David Alexander

PY - 2013/11/15

Y1 - 2013/11/15

N2 - Geometric detail is a universal phenomenon in real world objects. It is an important component in object modeling, but not accounted for in current intrinsic image works. In this work, we explore using a non-parametric method to separate geometric detail from intrinsic image components. We further decompose an image as albedo * (coarse-scale shading + shading detail). Our decomposition offers quantitative improvement in albedo recovery and material classification. Our method also enables interesting image editing activities, including bump removal, geometric detail smoothing/enhancement and material transfer.

AB - Geometric detail is a universal phenomenon in real world objects. It is an important component in object modeling, but not accounted for in current intrinsic image works. In this work, we explore using a non-parametric method to separate geometric detail from intrinsic image components. We further decompose an image as albedo * (coarse-scale shading + shading detail). Our decomposition offers quantitative improvement in albedo recovery and material classification. Our method also enables interesting image editing activities, including bump removal, geometric detail smoothing/enhancement and material transfer.

KW - Geometric detail

KW - intrinsic image decomposition

KW - material representation

UR - http://www.scopus.com/inward/record.url?scp=84887351506&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84887351506&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2013.129

DO - 10.1109/CVPR.2013.129

M3 - Conference article

AN - SCOPUS:84887351506

SP - 963

EP - 970

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

M1 - 6618973

ER -