D2-Net: A Trainable CNN for Joint Detection and Description 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.

arXiv commentAccepted at CVPR 2019

Cited by in corpus (6)

• Reference Pose Generation for Long-term Visual Localization via Learned Features and View Synthesis
• Leveraging Photogrammetric Mesh Models for Aerial-Ground Feature Point Matching Toward Integrated 3D Reconstruction
• Probabilistic Visual Place Recognition for Hierarchical Localization
• HarrisZ${}^{+}$: Harris Corner Selection for Next-Gen Image Matching Pipelines
• Visual Localization for Autonomous Driving: Mapping the Accurate Location in the City Maze
• CurriculumLoc: Enhancing Cross-Domain Geolocalization through Multi-Stage Refinement