Related papers: DynamicGlue: Epipolar and Time-Informed Data Association in Dynamic Environments using Graph Neural Networks

DynamicGlue: Epipolar and Time-Informed Data Association in Dynamic Environments using Graph Neural Networks

URL: http://arxiv.org/abs/2403.11370v3
Date: Mon, 1 Jul 2024 09:04:31 GMT
Title: DynamicGlue: Epipolar and Time-Informed Data Association in Dynamic Environments using Graph Neural Networks
Authors: Theresa Huber, Simon Schaefer, Stefan Leutenegger,
Abstract summary: We propose a graph neural network-based sparse feature matching network to perform robust matching under challenging conditions. We employ a similar scheme of attentional aggregation over graph edges to enhance keypoint representations as state-of-the-art feature-matching networks. A series of experiments show the superior performance of our network as it excludes keypoints on moving objects compared to state-of-the-art feature matching networks.
Score: 13.42760841894735
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: The assumption of a static environment is common in many geometric computer vision tasks like SLAM but limits their applicability in highly dynamic scenes. Since these tasks rely on identifying point correspondences between input images within the static part of the environment, we propose a graph neural network-based sparse feature matching network designed to perform robust matching under challenging conditions while excluding keypoints on moving objects. We employ a similar scheme of attentional aggregation over graph edges to enhance keypoint representations as state-of-the-art feature-matching networks but augment the graph with epipolar and temporal information and vastly reduce the number of graph edges. Furthermore, we introduce a self-supervised training scheme to extract pseudo labels for image pairs in dynamic environments from exclusively unprocessed visual-inertial data. A series of experiments show the superior performance of our network as it excludes keypoints on moving objects compared to state-of-the-art feature matching networks while still achieving similar results regarding conventional matching metrics. When integrated into a SLAM system, our network significantly improves performance, especially in highly dynamic scenes.