D
David G. Lowe
Researcher at University of British Columbia
Publications - 108
Citations - 91375
David G. Lowe is an academic researcher from University of British Columbia. The author has contributed to research in topics: Cognitive neuroscience of visual object recognition & Feature (computer vision). The author has an hindex of 52, co-authored 108 publications receiving 83353 citations. Previous affiliations of David G. Lowe include Courant Institute of Mathematical Sciences & Google.
Papers
More filters
Patent
Methods and apparatus for generating composite images
TL;DR: In this article, the authors provide apparatuses and methods for correcting position information of captured images received by position sensors based on alignment of overlapping images, which is then taken into account when displaying the locations of captured image on a display for providing guidance to users for generating composite images.
Modeling Positional Uncertainty in Object Recognition
Arthur R. Pope,David G. Lowe +1 more
TL;DR: This paper extends iterative alignment in the domain of 2D similarity transformations so that it represents the uncertainty in the position of each model and image feature, and that of the transformation estimate.
Proceedings ArticleDOI
Temporally coherent stereo: improving performance through knowledge of motion
V. Tucakov,David G. Lowe +1 more
TL;DR: The idea of temporally extending the results of a stereo algorithm in order to improve the algorithm's performance is introduced and speedups of up to 400% are achieved without significant errors.
Learning 3D Object Recognition Models from 2D Images
Arthur R. Pope,David G. Lowe +1 more
TL;DR: This work shows how to learn a model that represents a 3D object by a set of characteristic views, each defining a probability distribution over variation in object appearance, from a series of training images depicting a class of objects.
Proceedings Article
An adaptive interface for active localization
TL;DR: An approach for reducing the number of labelled training instances required to train an object classifier and for assisting the user in specifying optimal object location windows for training examples that are best aligned with the current classification function is presented.