Conditional Variational Autoencoders for Probabilistic Pose Regression

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zangeneh, Fereidoon, Bruns, Leonard, Dekel, Amit, Pieropan, Alessandro, Jensfelt, Patric
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909338673610752
author Zangeneh, Fereidoon
Bruns, Leonard
Dekel, Amit
Pieropan, Alessandro
Jensfelt, Patric
author_facet Zangeneh, Fereidoon
Bruns, Leonard
Dekel, Amit
Pieropan, Alessandro
Jensfelt, Patric
contents Robots rely on visual relocalization to estimate their pose from camera images when they lose track. One of the challenges in visual relocalization is repetitive structures in the operation environment of the robot. This calls for probabilistic methods that support multiple hypotheses for robot's pose. We propose such a probabilistic method to predict the posterior distribution of camera poses given an observed image. Our proposed training strategy results in a generative model of camera poses given an image, which can be used to draw samples from the pose posterior distribution. Our method is streamlined and well-founded in theory and outperforms existing methods on localization in presence of ambiguities.
format Preprint
id arxiv_https___arxiv_org_abs_2410_04989
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Conditional Variational Autoencoders for Probabilistic Pose Regression
Zangeneh, Fereidoon
Bruns, Leonard
Dekel, Amit
Pieropan, Alessandro
Jensfelt, Patric
Computer Vision and Pattern Recognition
Robots rely on visual relocalization to estimate their pose from camera images when they lose track. One of the challenges in visual relocalization is repetitive structures in the operation environment of the robot. This calls for probabilistic methods that support multiple hypotheses for robot's pose. We propose such a probabilistic method to predict the posterior distribution of camera poses given an observed image. Our proposed training strategy results in a generative model of camera poses given an image, which can be used to draw samples from the pose posterior distribution. Our method is streamlined and well-founded in theory and outperforms existing methods on localization in presence of ambiguities.
title Conditional Variational Autoencoders for Probabilistic Pose Regression
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.04989