Towards Internet-scale multi-view stereo

This paper introduces an approach for enabling existing multi-view stereo methods to operate on extremely large unstructured photo collections. The main idea is to decompose the collection into a set of overlapping sets of photos that can be processed in parallel, and to merge the resulting reconstr...

Full description

Saved in:
Bibliographic Details
Main Authors: Furukawa, Yasutaka, Curless, Brian, Seitz, Steven M, Szeliski, Richard
Format: Conference Proceeding
Language:English
Subjects:
Algorithm design and analysis
Clustering algorithms
Constraint optimization
Filtering algorithms
Image reconstruction
Internet
Iterative algorithms
Merging
Robustness
Testing
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper introduces an approach for enabling existing multi-view stereo methods to operate on extremely large unstructured photo collections. The main idea is to decompose the collection into a set of overlapping sets of photos that can be processed in parallel, and to merge the resulting reconstructions. This overlapping clustering problem is formulated as a constrained optimization and solved iteratively. The merging algorithm, designed to be parallel and out-of-core, incorporates robust filtering steps to eliminate low-quality reconstructions and enforce global visibility constraints. The approach has been tested on several large datasets downloaded from Flickr.com, including one with over ten thousand images, yielding a 3D reconstruction with nearly thirty million points.
ISSN:1063-6919
DOI:10.1109/CVPR.2010.5539802