Paper Info
Title
Two-view matching with view synthesis revisited
Abstract
Wide-baseline matching focussing on problems with extreme viewpoint change is considered. We introduce the use of view synthesis with affine-covariant detectors to solve such problems and show that matching with the Hessian-Affine or MSER detectors outperforms the state-of-the-art ASIFT [19]. To minimise the loss of speed caused by view synthesis, we propose the Matching On Demand with view Synthesis algorithm (MODS) that uses progressively more synthesized images and more (time-consuming) detectors until reliable estimation of geometry is possible. We show experimentally that the MODS algorithm solves problems beyond the state-of-the-art and yet is comparable in speed to standard wide-baseline matchers on simpler problems. Minor contributions include an improved method for tentative correspondence selection, applicable both with and without view synthesis and a view synthesis setup greatly improving MSER robustness to blur and scale change that increase its running time by 10% only.
Year
DOI
Venue
2013
10.1109/IVCNZ.2013.6727054
Image and Vision Computing New Zealand
Keywords
Field
DocType
Hessian matrices,affine transforms,image matching,Hessian-Affine detectors,MODS,MSER detectors,geometry estimation,image synthesis,matching on demand with view synthesis algorithm,time-consuming detectors,two view matching,view synthesis revisited,wide baseline matching,feature extraction,image matching,view synthesis
Computer vision,On demand,Image matching,Computer science,Robustness (computer science),View synthesis,Artificial intelligence,Detector
Conference
Volume
ISSN
ISBN
abs/1306.3855
2151-2191
978-1-4799-0882-0
Citations 
PageRank 
References 
6
0.45
15
Authors
3
Name
Order
Citations
PageRank
Dmytro Mishkin117510.20
Michal Perdoch268530.79
Jiri Matas328314.03