Probabilistic Spatial Distribution Prior Based Attentional Keypoints Matching Network

TL;DR

This paper introduces a novel keypoints matching network that incorporates IMU-based spatial distribution priors into an attentional graph neural network, improving matching accuracy and efficiency in image-based applications like SLAM.

Contribution

It proposes a probabilistic attention framework that integrates inertial sensor data as spatial priors into keypoints matching, a novel approach enhancing existing deep learning methods.

Findings

Improved matching accuracy on visual SLAM datasets.

Reduced network complexity due to spatial prior integration.

Demonstrated efficiency in real-world image matching tasks.

Abstract

Keypoints matching is a pivotal component for many image-relevant applications such as image stitching, visual simultaneous localization and mapping (SLAM), and so on. Both handcrafted-based and recently emerged deep learning-based keypoints matching methods merely rely on keypoints and local features, while losing sight of other available sensors such as inertial measurement unit (IMU) in the above applications. In this paper, we demonstrate that the motion estimation from IMU integration can be used to exploit the spatial distribution prior of keypoints between images. To this end, a probabilistic perspective of attention formulation is proposed to integrate the spatial distribution prior into the attentional graph neural network naturally. With the assistance of spatial distribution prior, the effort of the network for modeling the hidden features can be reduced. Furthermore, we present a projection loss for the proposed keypoints matching network, which gives a smooth edge between matching and un-matching keypoints. Image matching experiments on visual SLAM datasets indicate the effectiveness and efficiency of the presented method.