A Novel One-To-One Framework for Relative Camera Pose Estimation

To address the challenge of relative camera pose estimation, many permutation-invariant neural networks have been developed to process sparse correspondences with constant latency. These networks typically utilize an n -to- n framework, where n putative correspondences from the same image pairs are...

Full description

Saved in:
Bibliographic Details
Published inIEEE access p. 1
Main Authors Fatih Aydogdu, M., Fatih Demirci, M.
Format Journal Article
LanguageEnglish
Published IEEE 07.10.2024
Subjects
Cameras
Computational modeling
Computer architecture
Convolutional neural networks
Deep learning
Encoding
essential matrix
Feature extraction
Iterative algorithms
Pipelines
Pose estimation
RANSAC
relative camera pose estimation
stereo images
tensor processing units
Tensors
Training
Online AccessGet full text

Cover

More Information
Summary:To address the challenge of relative camera pose estimation, many permutation-invariant neural networks have been developed to process sparse correspondences with constant latency. These networks typically utilize an n -to- n framework, where n putative correspondences from the same image pairs are placed in distinct batch instances without any specific order. This uncorrelated set-type input structure does not sufficiently facilitate the extraction of contextual information for the correspondences. In this paper, we introduce a novel one -to- one framework designed to maximize context interaction within the network. Our framework prioritizes providing specialized context for each correspondence and enhancing the interaction of context data and correspondence data through a carefully designed input structure and network architecture schema. We conducted a series of experiments using various architectures within the one -to- one framework. Our results demonstrate that one -to- one networks not only matches but often surpasses the performance of traditional n -to- n networks, highlighting the one -to- one framework's significant potential and efficacy. To ensure a fair comparison, all one -to- one and n -to- n networks were trained on Google's Tensor Processing Units (TPUs). Notably, the memory capacity of a single TPUv4 device is sufficient to train one -to- one networks presented without generating TPU pods using multiple devices.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2024.3476238