Paper ID: 2204.08870

OpenGlue: Open Source Graph Neural Net Based Pipeline for Image Matching

Ostap Viniavskyi, Mariia Dobko, Dmytro Mishkin, Oles Dobosevych

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.

Submitted: Apr 19, 2022