Detecting 3D geometric boundaries of indoor scenes under varying lighting

Jie Ni; Tim K. Marks; Oncel Tuzel; Fatih Porikli

doi:10.1109/WACV.2014.6836125

Detecting 3D geometric boundaries of indoor scenes under varying lighting

Jie Ni, Tim K. Marks, Oncel Tuzel, Fatih Porikli

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › peer-review

1 Citation (Scopus)

Abstract

The goal of this research is to identify 3D geometric boundaries in a set of 2D photographs of a static indoor scene under unknown, changing lighting conditions. A 3D geometric boundary is a contour located at a 3D depth discontinuity or a discontinuity in the surface normal. These boundaries can be used effectively for reasoning about the 3D layout of a scene. To distinguish 3D geometric boundaries from 2D texture edges, we analyze the illumination subspace of local appearance at each image location. In indoor time-lapse photography and surveillance video, we frequently see images that are lit by unknown combinations of uncalibrated light sources. We introduce an algorithm for semi-binary nonnegative matrix factorization (SBNMF) to decompose such images into a set of lighting basis images, each of which shows the scene lit by a single light source. These basis images provide a natural, succinct representation of the scene, enabling tasks such as scene editing (e.g., relighting) and shadow edge identification.

Original language	English
Title of host publication	2014 IEEE Winter Conference on Applications of Computer Vision, WACV 2014
Publisher	IEEE Computer Society
Pages	1-8
Number of pages	8
ISBN (Print)	9781479949854
DOIs	https://doi.org/10.1109/WACV.2014.6836125
Publication status	Published - 2014
Event	2014 IEEE Winter Conference on Applications of Computer Vision, WACV 2014 - Steamboat Springs, CO, United States Duration: 24 Mar 2014 → 26 Mar 2014

Publication series

Name	2014 IEEE Winter Conference on Applications of Computer Vision, WACV 2014

Conference

Conference	2014 IEEE Winter Conference on Applications of Computer Vision, WACV 2014
Country/Territory	United States
City	Steamboat Springs, CO
Period	24/03/14 → 26/03/14

Access to Document

10.1109/WACV.2014.6836125

Cite this

Ni, J., Marks, T. K., Tuzel, O., & Porikli, F. (2014). Detecting 3D geometric boundaries of indoor scenes under varying lighting. In 2014 IEEE Winter Conference on Applications of Computer Vision, WACV 2014 (pp. 1-8). Article 6836125 (2014 IEEE Winter Conference on Applications of Computer Vision, WACV 2014). IEEE Computer Society. https://doi.org/10.1109/WACV.2014.6836125

@inproceedings{1134bdd1faeb4129b495a4def31ec1f2,

title = "Detecting 3D geometric boundaries of indoor scenes under varying lighting",

abstract = "The goal of this research is to identify 3D geometric boundaries in a set of 2D photographs of a static indoor scene under unknown, changing lighting conditions. A 3D geometric boundary is a contour located at a 3D depth discontinuity or a discontinuity in the surface normal. These boundaries can be used effectively for reasoning about the 3D layout of a scene. To distinguish 3D geometric boundaries from 2D texture edges, we analyze the illumination subspace of local appearance at each image location. In indoor time-lapse photography and surveillance video, we frequently see images that are lit by unknown combinations of uncalibrated light sources. We introduce an algorithm for semi-binary nonnegative matrix factorization (SBNMF) to decompose such images into a set of lighting basis images, each of which shows the scene lit by a single light source. These basis images provide a natural, succinct representation of the scene, enabling tasks such as scene editing (e.g., relighting) and shadow edge identification.",

author = "Jie Ni and Marks, \{Tim K.\} and Oncel Tuzel and Fatih Porikli",

year = "2014",

doi = "10.1109/WACV.2014.6836125",

language = "English",

isbn = "9781479949854",

series = "2014 IEEE Winter Conference on Applications of Computer Vision, WACV 2014",

publisher = "IEEE Computer Society",

pages = "1--8",

booktitle = "2014 IEEE Winter Conference on Applications of Computer Vision, WACV 2014",

address = "United States",

note = "2014 IEEE Winter Conference on Applications of Computer Vision, WACV 2014 ; Conference date: 24-03-2014 Through 26-03-2014",

}

Ni, J, Marks, TK, Tuzel, O & Porikli, F 2014, Detecting 3D geometric boundaries of indoor scenes under varying lighting. in 2014 IEEE Winter Conference on Applications of Computer Vision, WACV 2014., 6836125, 2014 IEEE Winter Conference on Applications of Computer Vision, WACV 2014, IEEE Computer Society, pp. 1-8, 2014 IEEE Winter Conference on Applications of Computer Vision, WACV 2014, Steamboat Springs, CO, United States, 24/03/14. https://doi.org/10.1109/WACV.2014.6836125

Detecting 3D geometric boundaries of indoor scenes under varying lighting. / Ni, Jie; Marks, Tim K.; Tuzel, Oncel et al.
2014 IEEE Winter Conference on Applications of Computer Vision, WACV 2014. IEEE Computer Society, 2014. p. 1-8 6836125 (2014 IEEE Winter Conference on Applications of Computer Vision, WACV 2014).

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › peer-review

TY - GEN

T1 - Detecting 3D geometric boundaries of indoor scenes under varying lighting

AU - Ni, Jie

AU - Marks, Tim K.

AU - Tuzel, Oncel

AU - Porikli, Fatih

PY - 2014

Y1 - 2014

N2 - The goal of this research is to identify 3D geometric boundaries in a set of 2D photographs of a static indoor scene under unknown, changing lighting conditions. A 3D geometric boundary is a contour located at a 3D depth discontinuity or a discontinuity in the surface normal. These boundaries can be used effectively for reasoning about the 3D layout of a scene. To distinguish 3D geometric boundaries from 2D texture edges, we analyze the illumination subspace of local appearance at each image location. In indoor time-lapse photography and surveillance video, we frequently see images that are lit by unknown combinations of uncalibrated light sources. We introduce an algorithm for semi-binary nonnegative matrix factorization (SBNMF) to decompose such images into a set of lighting basis images, each of which shows the scene lit by a single light source. These basis images provide a natural, succinct representation of the scene, enabling tasks such as scene editing (e.g., relighting) and shadow edge identification.

AB - The goal of this research is to identify 3D geometric boundaries in a set of 2D photographs of a static indoor scene under unknown, changing lighting conditions. A 3D geometric boundary is a contour located at a 3D depth discontinuity or a discontinuity in the surface normal. These boundaries can be used effectively for reasoning about the 3D layout of a scene. To distinguish 3D geometric boundaries from 2D texture edges, we analyze the illumination subspace of local appearance at each image location. In indoor time-lapse photography and surveillance video, we frequently see images that are lit by unknown combinations of uncalibrated light sources. We introduce an algorithm for semi-binary nonnegative matrix factorization (SBNMF) to decompose such images into a set of lighting basis images, each of which shows the scene lit by a single light source. These basis images provide a natural, succinct representation of the scene, enabling tasks such as scene editing (e.g., relighting) and shadow edge identification.

UR - https://www.scopus.com/pages/publications/84904627891

U2 - 10.1109/WACV.2014.6836125

DO - 10.1109/WACV.2014.6836125

M3 - Conference Paper

SN - 9781479949854

T3 - 2014 IEEE Winter Conference on Applications of Computer Vision, WACV 2014

SP - 1

EP - 8

BT - 2014 IEEE Winter Conference on Applications of Computer Vision, WACV 2014

PB - IEEE Computer Society

T2 - 2014 IEEE Winter Conference on Applications of Computer Vision, WACV 2014

Y2 - 24 March 2014 through 26 March 2014

ER -

Detecting 3D geometric boundaries of indoor scenes under varying lighting

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this