Building Rome in a Day.
We present a system that can reconstruct 3D geometry from large, unorganized collections of photographs such as those found by searching for a given city (e.g., Rome) on Internet photo-sharing sites. Our system is built on a set of new, distributed computer vision algorithms for image matching and 3...
| Published in: | Communications of the ACM Vol. 54; no. 10; pp. 105 - 113 |
|---|---|
| Main Authors: | , , , , , , |
| Format: | Article |
| Published: |
Association for Computing Machinery
Oct2011
|
| Subjects: | |
| Online Access: | View this record in EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=66736046&site=ehost-live header: @attributes: shortDbName: hlh uiTerm: 66736046 longDbName: Humanities International Complete uiTag: AN controlInfo: bkinfo: jinfo: jid: 00010782 ACM jtl: Communications of the ACM issn: 00010782 maglogo: N pubinfo: dt: Oct2011 vid: 54 iid: 10 pid: 68 pub: Association for Computing Machinery artinfo: ui: 66736046 10.1145/2001269.2001293 ppf: 105 ppct: 8 formats: tig: atl: Building Rome in a Day. aug: au: Agarwal, Sameer Furukawa, Yasutaka Simon, Ian Szeliski, Richard Seitz, Steven M. Curless, Brian Snavely, Noah affil: Google Inc., Seattle, WA. Microsoft Corporation, Redmond, WA. Microsoft Research, Redmond, WA. Google Inc. & University of Washington, Washington, Seattle, WA. University of Washington, Washington, Seattle, WA. Cornell University, Ithaca, NY. su: Three-dimensional imaging Photograph collections Computer vision Image processing Computer network resources Rome (Italy) Italy sug: subj: Rome (Italy) Italy Three-dimensional imaging Photograph collections Computer vision Image processing Computer network resources ab: We present a system that can reconstruct 3D geometry from large, unorganized collections of photographs such as those found by searching for a given city (e.g., Rome) on Internet photo-sharing sites. Our system is built on a set of new, distributed computer vision algorithms for image matching and 3D reconstruction, designed to maximize parallelism at each stage of the pipeline and to scale gracefully with both the size of the problem and the amount of available computation. Our experimental results demonstrate that it is now possible to reconstruct city-scale image collections with more than a hundred thousand images in less than a day. pubtype: Periodical doctype: Article src: R language: English refInfo: copyright: @attributes: flag: Y dt: @attributes: year: 2011 holdings: @attributes: islocal: N |
|---|