Real-Time Learning of Accurate Patch Rectification

14 years 2 months ago
Real-Time Learning of Accurate Patch Rectification
Recent work [5, 6] showed that learning-based patch rectification methods are both faster and more reliable than affine region methods. Unfortunately, their performance improvements are founded in a computationally expensive offline learning stage, which is not possible for applications such as SLAM. In this paper we propose an approach whose training stage is fast enough to be performed at run-time without the loss of accuracy or robustness. To this end, we developed a very fast method to compute the mean appearances of the feature points over sets of small variations that span the range of possible camera viewpoints. Then, by simply matching incoming feature points against these mean appearances, we get a coarse estimate of the viewpoint that is refined afterwards. Because there is no need to compute descriptors for the input image, the method is very fast at run-time. We demonstrate our approach on trackingby- detection for SLAM, real-time object detection and pose ...
Stefan Hinterstoisser, Oliver Kutter, Nassir Navab
Added 23 Jul 2009
Updated 10 Dec 2009
Type Conference
Year 2009
Where CVPR
Authors Stefan Hinterstoisser, Oliver Kutter, Nassir Navab, Pascal Fua, Vincent Lepetit
Comments (0)