000151674 001__ 151674
000151674 005__ 20190316234853.0
000151674 0247_ $$2doi$$a10.1007/s11263-010-0379-x
000151674 022__ $$a0920-5691
000151674 02470 $$2ISI$$a000286118400006
000151674 037__ $$aARTICLE
000151674 245__ $$aLearning Real-Time Perspective Patch Rectification
000151674 269__ $$a2011
000151674 260__ $$bSpringer Verlag$$c2011
000151674 336__ $$aJournal Articles
000151674 520__ $$aWe propose two learning-based methods to patch rectification that are faster and more reliable than state-of-the-art affine region detection methods. Given a reference view of a patch, they can quickly recognize it in new views and accurately estimate the homography between the reference view and the new view. Our methods are more memory-consuming than affine region detectors, and are in practice currently limited to a few tens of patches. However, if the reference image is a fronto-parallel view and the internal parameters known, one single patch is often enough to precisely estimate an object pose. As a result, we can deal in real-time with objects that are significantly less textured than the ones required by state-of-the-art methods.
000151674 6531_ $$aComputer Vision
000151674 6531_ $$aObject Detection
000151674 6531_ $$a3D Object Detection
000151674 700__ $$aHinterstoisser, S.
000151674 700__ $$0240235$$g149007$$aLepetit, V.
000151674 700__ $$aBenhimane, S.
000151674 700__ $$g112366$$aFua, P.$$0240252
000151674 700__ $$aNavab, N.
000151674 773__ $$j91$$tInternational Journal of Computer Vision$$k1$$q107--130
000151674 8564_ $$uhttps://infoscience.epfl.ch/record/151674/files/hinterstoisser_ijcv10.pdf$$zn/a$$s8123335$$yn/a
000151674 909C0 $$xU10659$$0252087$$pCVLAB
000151674 909CO $$qGLOBAL_SET$$pIC$$ooai:infoscience.tind.io:151674$$particle
000151674 917Z8 $$x149007
000151674 917Z8 $$x112366
000151674 937__ $$aEPFL-ARTICLE-151674
000151674 973__ $$rREVIEWED$$sPUBLISHED$$aEPFL
000151674 980__ $$aARTICLE