SuperGlue: Learning Feature Matching With Graph Neural Networks
Abstrak
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 github.com/magicleap/SuperGluePretrainedNetwork.
Topik & Kata Kunci
Penulis (4)
Paul-Edouard Sarlin
Daniel DeTone
Tomasz Malisiewicz
A. Rabinovich
Akses Cepat
- Tahun Terbit
- 2019
- Bahasa
- en
- Total Sitasi
- 2616×
- Sumber Database
- Semantic Scholar
- DOI
- 10.1109/cvpr42600.2020.00499
- Akses
- Open Access ✓