. . "P(GBP103/12/G084), P(TE01020415)" . "Two-View Matching with View Synthesis Revisited"@en . . . . . "Mishkin, Dmytro" . "Two-View Matching with View Synthesis Revisited" . "3"^^ . "Matas, Ji\u0159\u00ED" . . "3"^^ . . . . "RIV/68407700:21230/13:00212526!RIV14-TA0-21230___" . . . . "RIV/68407700:21230/13:00212526" . . "matching; wide baseline stereo; MSER; SIFT; extreme views"@en . . "[50F32AFFD3F9]" . . "Wide-baseline matching, focussing on challenging problems e.g. 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. 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 matching 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 discovery of a view synthesis set up greatly improving MSER robustness to blur and scale change that increase its running time by 10% only." . . "Two-View Matching with View Synthesis Revisited"@en . . "112202" . "Mishkin, Dmytro" . "Per\u010Foch, Michal" . "Wide-baseline matching, focussing on challenging problems e.g. 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. 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 matching 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 discovery of a view synthesis set up greatly improving MSER robustness to blur and scale change that increase its running time by 10% only."@en . "21230" . "Two-View Matching with View Synthesis Revisited" . . "Per\u010Foch, Michal" .