An Approximate Shading Model with Detail Decomposition for Object Relighting

Zicheng Liao, Kevin Karsch, Hongyi Zhang, David Alexander Forsyth

Research output: Contribution to journalArticle

Abstract

We present an object relighting system that allows an artist to select an object from an image and insert it into a target scene. Through simple interactions, the system can adjust illumination on the inserted object so that it appears naturally in the scene. To support image-based relighting, we build object model from the image, and propose a perceptually-inspired approximate shading model for the relighting. It decomposes the shading field into (a) a rough shape term that can be reshaded, (b) a parametric shading detail that encodes missing features from the first term, and (c) a geometric detail term that captures fine-scale material properties. With this decomposition, the shading model combines 3D rendering and image-based composition and allows more flexible compositing than image-based methods. Quantitative evaluation and a set of user studies suggest our method is a promising alternative to existing methods of object insertion.

LanguageEnglish (US)
Pages22-37
Number of pages16
JournalInternational Journal of Computer Vision
Volume127
Issue number1
DOIs
StatePublished - Jan 15 2019

Fingerprint

Decomposition
Materials properties
Lighting
Chemical analysis

Keywords

  • Image relighting
  • Image-based modeling
  • Object insertion
  • Shading model

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

An Approximate Shading Model with Detail Decomposition for Object Relighting. / Liao, Zicheng; Karsch, Kevin; Zhang, Hongyi; Forsyth, David Alexander.

In: International Journal of Computer Vision, Vol. 127, No. 1, 15.01.2019, p. 22-37.

Research output: Contribution to journalArticle

@article{c36ae008e88b4bd7b76209f683705254,
title = "An Approximate Shading Model with Detail Decomposition for Object Relighting",
abstract = "We present an object relighting system that allows an artist to select an object from an image and insert it into a target scene. Through simple interactions, the system can adjust illumination on the inserted object so that it appears naturally in the scene. To support image-based relighting, we build object model from the image, and propose a perceptually-inspired approximate shading model for the relighting. It decomposes the shading field into (a) a rough shape term that can be reshaded, (b) a parametric shading detail that encodes missing features from the first term, and (c) a geometric detail term that captures fine-scale material properties. With this decomposition, the shading model combines 3D rendering and image-based composition and allows more flexible compositing than image-based methods. Quantitative evaluation and a set of user studies suggest our method is a promising alternative to existing methods of object insertion.",
keywords = "Image relighting, Image-based modeling, Object insertion, Shading model",
author = "Zicheng Liao and Kevin Karsch and Hongyi Zhang and Forsyth, {David Alexander}",
year = "2019",
month = "1",
day = "15",
doi = "10.1007/s11263-018-1090-6",
language = "English (US)",
volume = "127",
pages = "22--37",
journal = "International Journal of Computer Vision",
issn = "0920-5691",
publisher = "Springer Netherlands",
number = "1",

}

TY - JOUR

T1 - An Approximate Shading Model with Detail Decomposition for Object Relighting

AU - Liao, Zicheng

AU - Karsch, Kevin

AU - Zhang, Hongyi

AU - Forsyth, David Alexander

PY - 2019/1/15

Y1 - 2019/1/15

N2 - We present an object relighting system that allows an artist to select an object from an image and insert it into a target scene. Through simple interactions, the system can adjust illumination on the inserted object so that it appears naturally in the scene. To support image-based relighting, we build object model from the image, and propose a perceptually-inspired approximate shading model for the relighting. It decomposes the shading field into (a) a rough shape term that can be reshaded, (b) a parametric shading detail that encodes missing features from the first term, and (c) a geometric detail term that captures fine-scale material properties. With this decomposition, the shading model combines 3D rendering and image-based composition and allows more flexible compositing than image-based methods. Quantitative evaluation and a set of user studies suggest our method is a promising alternative to existing methods of object insertion.

AB - We present an object relighting system that allows an artist to select an object from an image and insert it into a target scene. Through simple interactions, the system can adjust illumination on the inserted object so that it appears naturally in the scene. To support image-based relighting, we build object model from the image, and propose a perceptually-inspired approximate shading model for the relighting. It decomposes the shading field into (a) a rough shape term that can be reshaded, (b) a parametric shading detail that encodes missing features from the first term, and (c) a geometric detail term that captures fine-scale material properties. With this decomposition, the shading model combines 3D rendering and image-based composition and allows more flexible compositing than image-based methods. Quantitative evaluation and a set of user studies suggest our method is a promising alternative to existing methods of object insertion.

KW - Image relighting

KW - Image-based modeling

KW - Object insertion

KW - Shading model

UR - http://www.scopus.com/inward/record.url?scp=85060338599&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060338599&partnerID=8YFLogxK

U2 - 10.1007/s11263-018-1090-6

DO - 10.1007/s11263-018-1090-6

M3 - Article

VL - 127

SP - 22

EP - 37

JO - International Journal of Computer Vision

T2 - International Journal of Computer Vision

JF - International Journal of Computer Vision

SN - 0920-5691

IS - 1

ER -