We propose AffineGlue, a method for joint two-view feature matching and
...
We introduce LightGlue, a deep neural network that learns to match local...
Semantic 2D maps are commonly used by humans and machines for navigation...
Humans can orient themselves in their 3D environments using simple 2D ma...
Localization and mapping is the foundational technology for augmented re...
Finding local features that are repeatable across multiple views is a
co...
Camera pose estimation in known scenes is a 3D geometry task recently ta...
This paper introduces SuperGlue, a neural network that matches two sets ...
Deep learning has enabled impressive progress in the accuracy of semanti...
Robust and accurate visual localization is a fundamental capability for
...
Many robotics applications require precise pose estimates despite operat...