SuperGlue: Learning Feature Matching with Graph Neural Networks

11/26/2019 ∙ by Paul-Edouard Sarlin, et al. ∙ 15

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.



There are no comments yet.


page 2

page 4

page 8

page 12

page 13

page 14

page 15

Code Repositories


SuperGlue: Learning Feature Matching with Graph Neural Networks (CVPR 2020, Oral)

view repo


Code & pretrained models of novel deep graph matching methods.

view repo


[SuperGlue: Learning Feature Matching with Graph Neural Networks] This repo includes PyTorch code for training the SuperGlue matching network on top of SIFT keypoints and descriptors.

view repo


End-to-end SFM framework based on GTSAM

view repo


SuperGlue-pytorch training

view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.