TY - EJOUR DO - 10.1007/s11263-010-0379-x AB - We 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. T1 - Learning Real-Time Perspective Patch Rectification IS - 1 DA - 2011 AU - Hinterstoisser, S. AU - Lepetit, V. AU - Benhimane, S. AU - Fua, P. AU - Navab, N. JF - International Journal of Computer Vision SP - 107--130 VL - 91 EP - 107--130 PB - Springer Verlag ID - 151674 KW - Computer Vision KW - Object Detection KW - 3D Object Detection SN - 0920-5691 UR - http://infoscience.epfl.ch/record/151674/files/hinterstoisser_ijcv10.pdf ER -