R2D2: Repeatable and Reliable Detector and Descriptor

Understand

Interest point detection and local feature description are fundamental steps in many computer vision applications.

• Classical methods for these tasks are based on a detect-then-describe paradigm where separate handcrafted methods are used to first identify repeatable keypoints and then represent them with a local descriptor.
• Neural networks trained with metric learning losses have recently caught up with these techniques, focusing on learning repeatable saliency maps for keypoint detection and learning descriptors at the detected keypoint locations.
• In this work, we argue that salient regions are not necessarily discriminative, and therefore can harm the performance of the description.