SuperGlue swMATH ID: 42666 Software Authors: Paul-Edouard Sarlin, Daniel DeTone, Tomasz Malisiewicz, Andrew Rabinovich Description: SuperGlue: Learning Feature Matching with Graph Neural Networks. This paper introduces SuperGlue, a neural network that matches two sets of local features by jointly finding correspondences and rejecting non-matchable points. Assignments are estimated by solving a differentiable optimal transport problem, whose costs are predicted by a graph neural network. We introduce a flexible context aggregation mechanism based on attention, enabling SuperGlue to reason about the underlying 3D scene and feature assignments jointly. Compared to traditional, hand-designed heuristics, our technique learns priors over geometric transformations and regularities of the 3D world through end-to-end training from image pairs. SuperGlue outperforms other learned approaches and achieves state-of-the-art results on the task of pose estimation in challenging real-world indoor and outdoor environments. The proposed method performs matching in real-time on a modern GPU and can be readily integrated into modern SfM or SLAM systems. The code and trained weights are publicly available at https://github.com/magicleap/SuperGluePretrainedNetwork Homepage: https://arxiv.org/abs/1911.11763 Source Code: https://github.com/magicleap/SuperGluePretrainedNetwork Dependencies: Python Related Software: D2-Net; ContextDesc; ASLFeat; SuperPoint; HPatches; LoFTR; Patch2Pix; BRISK; PointNet; SOSNet; L2-Net; Theia; R2D2; InLoc; ORB-SLAM2; ORB-SLAM; MAGSAC++; COTR; MS-COCO; FlowNet Cited in: 2 Publications all top 5 Cited by 6 Authors 1 Fan, Aoxiang 1 Jiang, Junjun 1 Jiang, Xingyu 1 Ma, Jiayi 1 Szeliski, Richard 1 Yan, Junchi Cited in 2 Serials 1 International Journal of Computer Vision 1 Texts in Computer Science Cited in 1 Field 2 Computer science (68-XX) Citations by Year