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 Mishkin | 1 | 175 | 10.20 |
Michal Perdoch | 2 | 685 | 30.79 |
Jiri Matas | 3 | 283 | 14.03 |