%0 Generic %1 sarlin2019superglue %A Sarlin, Paul-Edouard %A DeTone, Daniel %A Malisiewicz, Tomasz %A Rabinovich, Andrew %D 2019 %K featurepoints %T SuperGlue: Learning Feature Matching with Graph Neural Networks %U http://arxiv.org/abs/1911.11763 %X 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.

@misc{sarlin2019superglue, abstract = {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.}, added-at = {2021-09-26T05:39:09.000+0200}, author = {Sarlin, Paul-Edouard and DeTone, Daniel and Malisiewicz, Tomasz and Rabinovich, Andrew}, biburl = {https://www.bibsonomy.org/bibtex/276128a7584deb03f6e14374fd54c8b78/glgl3154}, description = {SuperGlue: Learning Feature Matching with Graph Neural Networks}, interhash = {ab9ca48e26417cb308aa89a12333a0db}, intrahash = {76128a7584deb03f6e14374fd54c8b78}, keywords = {featurepoints}, note = {cite arxiv:1911.11763Comment: Oral at CVPR 2020, with appendix and link to publicly available code}, timestamp = {2021-09-26T05:39:09.000+0200}, title = {SuperGlue: Learning Feature Matching with Graph Neural Networks}, url = {http://arxiv.org/abs/1911.11763}, year = 2019 }