Salvato in:
Dettagli Bibliografici
Autori principali: Patwardhan, Aalok, Rhodes, Callum, Bae, Gwangbin, Davison, Andrew J.
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2403.15583
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913279365873664
author Patwardhan, Aalok
Rhodes, Callum
Bae, Gwangbin
Davison, Andrew J.
author_facet Patwardhan, Aalok
Rhodes, Callum
Bae, Gwangbin
Davison, Andrew J.
contents Camera rotation estimation from a single image is a challenging task, often requiring depth data and/or camera intrinsics, which are generally not available for in-the-wild videos. Although external sensors such as inertial measurement units (IMUs) can help, they often suffer from drift and are not applicable in non-inertial reference frames. We present U-ARE-ME, an algorithm that estimates camera rotation along with uncertainty from uncalibrated RGB images. Using a Manhattan World assumption, our method leverages the per-pixel geometric priors encoded in single-image surface normal predictions and performs optimisation over the SO(3) manifold. Given a sequence of images, we can use the per-frame rotation estimates and their uncertainty to perform multi-frame optimisation, achieving robustness and temporal consistency. Our experiments demonstrate that U-ARE-ME performs comparably to RGB-D methods and is more robust than sparse feature-based SLAM methods. We encourage the reader to view the accompanying video at https://callum-rhodes.github.io/U-ARE-ME for a visual overview of our method.
format Preprint
id arxiv_https___arxiv_org_abs_2403_15583
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle U-ARE-ME: Uncertainty-Aware Rotation Estimation in Manhattan Environments
Patwardhan, Aalok
Rhodes, Callum
Bae, Gwangbin
Davison, Andrew J.
Computer Vision and Pattern Recognition
Camera rotation estimation from a single image is a challenging task, often requiring depth data and/or camera intrinsics, which are generally not available for in-the-wild videos. Although external sensors such as inertial measurement units (IMUs) can help, they often suffer from drift and are not applicable in non-inertial reference frames. We present U-ARE-ME, an algorithm that estimates camera rotation along with uncertainty from uncalibrated RGB images. Using a Manhattan World assumption, our method leverages the per-pixel geometric priors encoded in single-image surface normal predictions and performs optimisation over the SO(3) manifold. Given a sequence of images, we can use the per-frame rotation estimates and their uncertainty to perform multi-frame optimisation, achieving robustness and temporal consistency. Our experiments demonstrate that U-ARE-ME performs comparably to RGB-D methods and is more robust than sparse feature-based SLAM methods. We encourage the reader to view the accompanying video at https://callum-rhodes.github.io/U-ARE-ME for a visual overview of our method.
title U-ARE-ME: Uncertainty-Aware Rotation Estimation in Manhattan Environments
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.15583