Thumbnail
Access Restriction
Subscribed

Author Song Cao ♦ Snavely, N.
Source IEEE Xplore Digital Library
Content type Text
Publisher Institute of Electrical and Electronics Engineers, Inc. (IEEE)
File Format PDF
Copyright Year ©2014
Language English
Subject Domain (in DDC) Computer science, information & general works ♦ Data processing & computer science
Subject Keyword Databases ♦ Three-dimensional displays ♦ Probabilistic logic ♦ Computational modeling ♦ Image reconstruction ♦ Image recognition ♦ Solid modeling
Abstract How much data do we need to describe a location? We explore this question in the context of 3D scene reconstructions created from running structure from motion on large Internet photo collections, where reconstructions can contain many millions of 3D points. We consider several methods for computing much more compact representations of such reconstructions for the task of location recognition, with the goal of maintaining good performance with very small models. In particular, we introduce a new method for computing compact models that takes into account both image-point relationships and feature distinctiveness, and we show that this method produces small models that yield better recognition performance than previous model reduction techniques.
ISBN 9781479951185
ISSN 10636919
Educational Role Student ♦ Teacher
Age Range above 22 year
Educational Use Research ♦ Reading
Education Level UG and PG
Learning Resource Type Article
Publisher Date 2014-06-23
Publisher Place USA
Rights Holder Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Size (in Bytes) 682.91 kB
Page Count 8
Starting Page 461
Ending Page 468


Source: IEEE Xplore Digital Library