Calonder, MichaelLepetit, VincentFua, Pascal2010-11-302010-11-302010-11-30200810.1007/978-3-540-88682-2_6https://infoscience.epfl.ch/handle/20.500.14299/60848WOS:000260656000005Statistical learning techniques have been used to dramatically speed-up keypoint matching by training a classifier to recognize a specific set of keypoints. However, the training itself is usually relatively slow and performed offline. Although methods have recently been proposed to train the classifier online, they can only learn a very limited number of new keypoints. This represents a handicap for real-time applications, such as Simultaneous Localization and Mapping (SLAM), which require incremental addition of arbitrary numbers of keypoints as they become visible.Randomized Treestext::conference output::conference proceedings::conference paper