TU Darmstadt / ULB / TUbiblio

Multi-View Stereo for Community Photo Collections

Goesele, Michael and Snavely, Noah and Curless, Brian and Hoppe, Hugues and Seitz, Steven M. (2007):
Multi-View Stereo for Community Photo Collections.
IEEE 11th International Conference on Computer Vision, Rio de Janeiro, Brasil, October 14-20, 2007, [Conference or Workshop Item]

Abstract

We present a multi-view stereo algorithm that addresses the extreme changes in lighting, scale, clutter, and other effects in large online community photo collections. Our idea is to intelligently choose images to match, both at a per-view and per-pixel level. We show that such adaptive view selection enables robust performance even with dramatic appearance variability. The stereo matching technique takes as input sparse 3D points reconstructed from structure-from-motion methods and iteratively grows surfaces from these points. Optimizing for surface normals within a photoconsistency measure significantly improves the matching results. While the focus of our approach is to estimate high-quality depth maps, we also show examples of merging the resulting depth maps into compelling scene reconstructions. We demonstrate our algorithm on standard multi-view stereo datasets and on casually acquired photo collections of famous scenes gathered from the Internet.

Item Type: Conference or Workshop Item
Erschienen: 2007
Creators: Goesele, Michael and Snavely, Noah and Curless, Brian and Hoppe, Hugues and Seitz, Steven M.
Title: Multi-View Stereo for Community Photo Collections
Language: English
Abstract:

We present a multi-view stereo algorithm that addresses the extreme changes in lighting, scale, clutter, and other effects in large online community photo collections. Our idea is to intelligently choose images to match, both at a per-view and per-pixel level. We show that such adaptive view selection enables robust performance even with dramatic appearance variability. The stereo matching technique takes as input sparse 3D points reconstructed from structure-from-motion methods and iteratively grows surfaces from these points. Optimizing for surface normals within a photoconsistency measure significantly improves the matching results. While the focus of our approach is to estimate high-quality depth maps, we also show examples of merging the resulting depth maps into compelling scene reconstructions. We demonstrate our algorithm on standard multi-view stereo datasets and on casually acquired photo collections of famous scenes gathered from the Internet.

Uncontrolled Keywords: Forschungsgruppe Capturing Reality (CARE), Computer vision, Multi-view stereo, Internet, Community photo collections, Depth maps
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Graphics, Capture and Massively Parallel Computing
20 Department of Computer Science > Interactive Graphics Systems
Event Title: IEEE 11th International Conference on Computer Vision
Event Location: Rio de Janeiro, Brasil
Event Dates: October 14-20, 2007
Date Deposited: 16 Apr 2018 09:03
Official URL: http://download.hrz.tu-darmstadt.de/media/FB20/GCC/paper/Goe...
Export:
Suche nach Titel in: TUfind oder in Google
Send an inquiry Send an inquiry

Options (only for editors)
Show editorial Details Show editorial Details