scispace - formally typeset
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
Proceedings ArticleDOI

Hessian Methods For Verification Of 3D Model Parameters From 2D Image Data

Robert R. Goldberg, +1 more
TL;DR: A unified approach to instantiating model and camera parameters in the verification process is presented, simplifying the camera calibration problem and extending to vision applications with general models.
Book ChapterDOI

Measuring the Significance of Image Relations

David G. Lowe
TL;DR: This chapter will be to take a unified view of the many grouping phenomena by examining the underlying principles for measuring the significance of each grouping by arguing that certain image relations are carriers of statistical information indicating that they are non-accidental in origin.

Vision-based Mapping with Backward

Stephen Se, +2 more
TL;DR: This work considers the problem of creating a consistent alignment of multiple 3D submaps containing distinctive visual landmarks in an unmodified environment and proposes an eficient map alignment algorithm based on landmark specificity to align submaps.
Proceedings ArticleDOI

Improved generalization through learning a similarity metric and kernel size

David G. Lowe
TL;DR: Much better generalization can be obtained by using a variable interpolation kernel in combination with conjugate gradient optimization of the similarity metric and kernel size to form a variable-kernel similarity metric (VSM) learning.

Checking of 3 espondences

Daniel McReynolds, +1 more
TL;DR: An algorithm is described which rapidly verifies the potential rigidity of three-dimensional point correspondences from a pair of two-dimensional views under perspective projection and is integrated with a linear algorithm for 3D recovery due to Kontsevich.