swMATH ID: 42672
Software Authors: Mihai Dusmanu, Ignacio Rocco, Tomas Pajdla, Marc Pollefeys, Josef Sivic, Akihiko Torii, Torsten Sattler
Description: D2-Net: A Trainable CNN for Joint Detection and Description of Local Features. 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.
Homepage: https://arxiv.org/abs/1905.03561
Source Code:  https://github.com/mihaidusmanu/d2-net
Related Software: SuperPoint; HPatches; BRISK; R2D2; SuperGlue; ContextDesc; ASLFeat; LF-Net; PointNet; LoFTR; Patch2Pix; SOSNet; L2-Net; Theia; InLoc; ORB-SLAM2; ORB-SLAM; MAGSAC++; COTR; MS-COCO
Cited in: 3 Documents

Citations by Year