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

Code

• github.com/mihaidusmanu/d2-net
  OfficialIn paperpytorch★ 0
• github.com/naver/kapture
  none★ 533
• github.com/visinf/cad
  pytorch★ 31
• github.com/UditSinghParihar/d2-net
  pytorch★ 0

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.

Tasks

Benchmark Results

Reproductions