Pose-GNN : Camera Pose Estimation System Using Graph Neural Networks

TL;DR

This paper introduces Pose-GNN, a novel camera pose estimation system that leverages graph neural networks to improve localization accuracy in indoor and outdoor environments by modeling image features as graphs.

Contribution

The paper presents a new GNN-based approach for camera pose estimation, comparing two graph modeling strategies and demonstrating superior performance over existing methods.

Findings

GNN-based methods outperform traditional localization techniques.

Modeling image features as graphs enhances pose estimation accuracy.

Both indoor and outdoor environments benefit from the proposed approach.

Abstract

We propose a novel image based localization system using graph neural networks (GNN). The pretrained ResNet50 convolutional neural network (CNN) architecture is used to extract the important features for each image. Following, the extracted features are input to GNN to find the pose of each image by either using the image features as a node in a graph and formulate the pose estimation problem as node pose regression or modelling the image features themselves as a graph and the problem becomes graph pose regression. We do an extensive comparison between the proposed two approaches and the state of the art single image localization methods and show that using GNN leads to enhanced performance for both indoor and outdoor environments.