D2-Net: A Trainable CNN for Joint Description and Detection of Local Features

Abstract

In this work we address the problem of finding reliable pixel-level correspondences under difficult imaging conditions. We propose an approach where a single convolutional neural network plays a dual role: It is simultaneously a dense feature descriptor and a feature detector. By postponing the detection to a later stage, the obtained keypoints are more stable than their traditional counterparts based on early detection of low-level structures. We show that this model can be trained using pixel correspondences extracted from readily available large-scale SfM reconstructions, without any further annotations. The proposed method obtains state-of-the-art performance on both the difficult Aachen Day-Night localization dataset and the InLoc indoor localization benchmark, as well as competitive performance on other benchmarks for image matching and 3D reconstruction.

Keywords

Affiliated Institutions

• Microsoft Research (United Kingdom) GB
• Czech Technical University in Prague CZ
• Tokyo Institute of Technology JP
• Département d'Informatique FR
• ETH Zurich CH
• Université Paris Sciences et Lettres FR
• Institute of Informatics of the Slovak Academy of Sciences SK
• Institut national de recherche en sciences et technologies du numérique FR

Related Publications