DeepAI AI Chat
Log In Sign Up

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

by   Ahmed Elmoogy, et al.

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.


page 3

page 4


S3E-GNN: Sparse Spatial Scene Embedding with Graph Neural Networks for Camera Relocalization

Camera relocalization is the key component of simultaneous localization ...

Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation

Various deep learning techniques have been proposed to solve the single-...

Context Modeling in 3D Human Pose Estimation: A Unified Perspective

Estimating 3D human pose from a single image suffers from severe ambigui...

EEG-GNN: Graph Neural Networks for Classification of Electroencephalogram (EEG) Signals

Convolutional neural networks (CNN) have been frequently used to extract...

MR-GNN: Multi-Resolution and Dual Graph Neural Network for Predicting Structured Entity Interactions

Predicting interactions between structured entities lies at the core of ...

Spatio-Temporal Graph Localization Networks for Image-based Navigation

Localization in topological maps is essential for image-based navigation...

DeepCut: Unsupervised Segmentation using Graph Neural Networks Clustering

Image segmentation is a fundamental task in computer vision. Data annota...