Factored time-lapse video

Kalyan Sunkavalli; Wojciech Matusik; Hanspeter Pfister; Szymon Rusinkiewicz

doi:10.1145/1275808.1276504

Factored time-lapse video

Kalyan Sunkavalli
, Wojciech Matusik
, Hanspeter Pfister
, Szymon Rusinkiewicz

Computer Science

Research output: Contribution to conference › Paper › peer-review

34 Scopus citations

Abstract

We describe a method for converting time-lapse photography captured with outdoor cameras into Factored Time-Lapse Video (FTLV): a video in which time appears to move faster (i.e., lapsing) and where data at each pixel has been factored into shadow, illumination, and reflectance components. The factorization allows a user to easily relight the scene, recover a portion of the scene geometry (normals), and to perform advanced image editing operations. Our method is easy to implement, robust, and provides a compact representation with good reconstruction characteristics. We show results using several publicly available time-lapse sequences.

Original language	English (US)
DOIs	https://doi.org/10.1145/1275808.1276504
State	Published - 2007
Event	34th Annual Meeting of the Association for Computing Machinery's Special Interest Group on Graphics - San Diego, CA, United States Duration: Aug 5 2007 → Aug 9 2007

Other

Other	34th Annual Meeting of the Association for Computing Machinery's Special Interest Group on Graphics
Country/Territory	United States
City	San Diego, CA
Period	8/5/07 → 8/9/07

All Science Journal Classification (ASJC) codes

General Computer Science

Keywords

Computational photography
Image-based rendering and lighting
Inverse problems
Reflectance

Access to Document

10.1145/1275808.1276504

Cite this

@conference{ae8125b4d54b4c8f8515a189e2725f2c,

title = "Factored time-lapse video",

abstract = "We describe a method for converting time-lapse photography captured with outdoor cameras into Factored Time-Lapse Video (FTLV): a video in which time appears to move faster (i.e., lapsing) and where data at each pixel has been factored into shadow, illumination, and reflectance components. The factorization allows a user to easily relight the scene, recover a portion of the scene geometry (normals), and to perform advanced image editing operations. Our method is easy to implement, robust, and provides a compact representation with good reconstruction characteristics. We show results using several publicly available time-lapse sequences.",

keywords = "Computational photography, Image-based rendering and lighting, Inverse problems, Reflectance",

author = "Kalyan Sunkavalli and Wojciech Matusik and Hanspeter Pfister and Szymon Rusinkiewicz",

note = "Copyright: Copyright 2013 Elsevier B.V., All rights reserved.; 34th Annual Meeting of the Association for Computing Machinery's Special Interest Group on Graphics ; Conference date: 05-08-2007 Through 09-08-2007",

year = "2007",

doi = "10.1145/1275808.1276504",

language = "English (US)",

}

TY - CONF

T1 - Factored time-lapse video

AU - Sunkavalli, Kalyan

AU - Matusik, Wojciech

AU - Pfister, Hanspeter

AU - Rusinkiewicz, Szymon

PY - 2007

Y1 - 2007

N2 - We describe a method for converting time-lapse photography captured with outdoor cameras into Factored Time-Lapse Video (FTLV): a video in which time appears to move faster (i.e., lapsing) and where data at each pixel has been factored into shadow, illumination, and reflectance components. The factorization allows a user to easily relight the scene, recover a portion of the scene geometry (normals), and to perform advanced image editing operations. Our method is easy to implement, robust, and provides a compact representation with good reconstruction characteristics. We show results using several publicly available time-lapse sequences.

AB - We describe a method for converting time-lapse photography captured with outdoor cameras into Factored Time-Lapse Video (FTLV): a video in which time appears to move faster (i.e., lapsing) and where data at each pixel has been factored into shadow, illumination, and reflectance components. The factorization allows a user to easily relight the scene, recover a portion of the scene geometry (normals), and to perform advanced image editing operations. Our method is easy to implement, robust, and provides a compact representation with good reconstruction characteristics. We show results using several publicly available time-lapse sequences.

KW - Computational photography

KW - Image-based rendering and lighting

KW - Inverse problems

KW - Reflectance

UR - https://www.scopus.com/pages/publications/57149102129

UR - https://www.scopus.com/pages/publications/57149102129#tab=citedBy

U2 - 10.1145/1275808.1276504

DO - 10.1145/1275808.1276504

M3 - Paper

AN - SCOPUS:57149102129

T2 - 34th Annual Meeting of the Association for Computing Machinery's Special Interest Group on Graphics

Y2 - 5 August 2007 through 9 August 2007

ER -

Factored time-lapse video

Abstract

Other

All Science Journal Classification (ASJC) codes

Keywords

Access to Document

Other files and links

Fingerprint

Cite this