Extending 6D Object Pose Estimators for Stereo Vision

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pöllabauer, Thomas, Emrich, Jan, Knauthe, Volker, Kuijper, Arjan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929493666430976
author Pöllabauer, Thomas
Emrich, Jan
Knauthe, Volker
Kuijper, Arjan
author_facet Pöllabauer, Thomas
Emrich, Jan
Knauthe, Volker
Kuijper, Arjan
contents Estimating the 6D pose of objects accurately, quickly, and robustly remains a difficult task. However, recent methods for directly regressing poses from RGB images using dense features have achieved state-of-the-art results. Stereo vision, which provides an additional perspective on the object, can help reduce pose ambiguity and occlusion. Moreover, stereo can directly infer the distance of an object, while mono-vision requires internalized knowledge of the object's size. To extend the state-of-the-art in 6D object pose estimation to stereo, we created a BOP compatible stereo version of the YCB-V dataset. Our method outperforms state-of-the-art 6D pose estimation algorithms by utilizing stereo vision and can easily be adopted for other dense feature-based algorithms.
format Preprint
id arxiv_https___arxiv_org_abs_2402_05610
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Extending 6D Object Pose Estimators for Stereo Vision
Pöllabauer, Thomas
Emrich, Jan
Knauthe, Volker
Kuijper, Arjan
Computer Vision and Pattern Recognition
Artificial Intelligence
Estimating the 6D pose of objects accurately, quickly, and robustly remains a difficult task. However, recent methods for directly regressing poses from RGB images using dense features have achieved state-of-the-art results. Stereo vision, which provides an additional perspective on the object, can help reduce pose ambiguity and occlusion. Moreover, stereo can directly infer the distance of an object, while mono-vision requires internalized knowledge of the object's size. To extend the state-of-the-art in 6D object pose estimation to stereo, we created a BOP compatible stereo version of the YCB-V dataset. Our method outperforms state-of-the-art 6D pose estimation algorithms by utilizing stereo vision and can easily be adopted for other dense feature-based algorithms.
title Extending 6D Object Pose Estimators for Stereo Vision
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2402.05610