CaltechAUTHORS
  A Caltech Library Service

Automating joiners

Zelnik-Manor, Lihi and Perona, Pietro (2007) Automating joiners. In: NPAR '07 Proceedings of the 5th international symposium on Non-photorealistic animation and rendering. Association for Computing Machinery , New York, NY, pp. 121-131. ISBN 978-1-59593-624-0. https://resolver.caltech.edu/CaltechAUTHORS:20100503-111327744

[img]
Preview
PDF - Published Version
See Usage Policy.

13Mb

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20100503-111327744

Abstract

Pictures taken from different view points cannot be stitched into a geometrically consistent mosaic, unless the structure of the scene is very special. However, geometrical consistency is not the only criterion for success: incorporating multiple view points into the same picture may produce compelling and informative representations. A multi viewpoint form of visual expression that has recently become highly popular is that of joiners (a term coined by artist David Hockney). Joiners are compositions where photographs are layered on a 2D canvas, with some photographs occluding others and boundaries fully visible. Composing joiners is currently a tedious manual process, especially when a great number of photographs is involved. We are thus interested in automating their construction. Our approach is based on optimizing a cost function encouraging image-to-image consistency which is measured on point-features and along picture boundaries. The optimization looks for consistency in the 2D composition rather than 3D geometrical scene consistency and explicitly considers occlusion between pictures. We illustrate our ideas with a number of experiments on collections of images of objects, people, and outdoor scenes.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
http://doi.acm.org/10.1145/1274871.1274890DOIUNSPECIFIED
http://portal.acm.org/citation.cfm?id=1274871.1274890&coll=ACM&dl=ACM&CFID=88935759&CFTOKEN=76366106PublisherUNSPECIFIED
ORCID:
AuthorORCID
Perona, Pietro0000-0002-7583-5809
Additional Information:© 2007 Association for Computing Machinery, Inc. Year of Publication: 2007. We wish to thank David Lowe and Maneesh Agrawala for reading earlier versions of this paper and providing useful comments, Matthew Brown for his Autostitch software, the Oxford Visual Geometry Group for their edge detection code. This research was supported by MURI award number AS3318 and the Center of Neuromorphic Systems Engineering award EEC-9402726.
Funders:
Funding AgencyGrant Number
MURI awardAS3318
Center of Neuromorphic Systems Engineering awardEEC-9402726
Subject Keywords:multiple view point; panorama; mosaic; joiner; composition
Record Number:CaltechAUTHORS:20100503-111327744
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20100503-111327744
Official Citation:Zelnik-Manor, L. and P. Perona (2007). Automating joiners. Proceedings of the 5th international symposium on Non-photorealistic animation and rendering. San Diego, California, ACM: 121-131. http://doi.acm.org/10.1145/1274871.1274890
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:18107
Collection:CaltechAUTHORS
Deposited By: Jason Perez
Deposited On:24 Jun 2010 17:57
Last Modified:03 Oct 2019 01:38

Repository Staff Only: item control page