OpenGlue: Open Source Graph Neural Net Based Pipeline for Image Matching
This work provides a free, open-source solution for image matching tasks, benefiting researchers and practitioners in computer vision, though it is incremental as it builds upon existing methods like SuperGlue.
The authors tackled the problem of image matching by developing OpenGlue, an open-source framework using a Graph Neural Network-based matcher, which improved performance by incorporating additional geometrical information like local feature scale and orientation, achieving significant accuracy gains as shown in their experiments.
We present OpenGlue: a free open-source framework for image matching, that uses a Graph Neural Network-based matcher inspired by SuperGlue \cite{sarlin20superglue}. We show that including additional geometrical information, such as local feature scale, orientation, and affine geometry, when available (e.g. for SIFT features), significantly improves the performance of the OpenGlue matcher. We study the influence of the various attention mechanisms on accuracy and speed. We also present a simple architectural improvement by combining local descriptors with context-aware descriptors. The code and pretrained OpenGlue models for the different local features are publicly available.