Volumetric Semantically Consistent 3D Panoptic Mapping

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Miao, Yang, Armeni, Iro, Pollefeys, Marc, Barath, Daniel
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913419962089472
author Miao, Yang
Armeni, Iro
Pollefeys, Marc
Barath, Daniel
author_facet Miao, Yang
Armeni, Iro
Pollefeys, Marc
Barath, Daniel
contents We introduce an online 2D-to-3D semantic instance mapping algorithm aimed at generating comprehensive, accurate, and efficient semantic 3D maps suitable for autonomous agents in unstructured environments. The proposed approach is based on a Voxel-TSDF representation used in recent algorithms. It introduces novel ways of integrating semantic prediction confidence during mapping, producing semantic and instance-consistent 3D regions. Further improvements are achieved by graph optimization-based semantic labeling and instance refinement. The proposed method achieves accuracy superior to the state of the art on public large-scale datasets, improving on a number of widely used metrics. We also highlight a downfall in the evaluation of recent studies: using the ground truth trajectory as input instead of a SLAM-estimated one substantially affects the accuracy, creating a large gap between the reported results and the actual performance on real-world data.
format Preprint
id arxiv_https___arxiv_org_abs_2309_14737
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Volumetric Semantically Consistent 3D Panoptic Mapping
Miao, Yang
Armeni, Iro
Pollefeys, Marc
Barath, Daniel
Robotics
Computer Vision and Pattern Recognition
We introduce an online 2D-to-3D semantic instance mapping algorithm aimed at generating comprehensive, accurate, and efficient semantic 3D maps suitable for autonomous agents in unstructured environments. The proposed approach is based on a Voxel-TSDF representation used in recent algorithms. It introduces novel ways of integrating semantic prediction confidence during mapping, producing semantic and instance-consistent 3D regions. Further improvements are achieved by graph optimization-based semantic labeling and instance refinement. The proposed method achieves accuracy superior to the state of the art on public large-scale datasets, improving on a number of widely used metrics. We also highlight a downfall in the evaluation of recent studies: using the ground truth trajectory as input instead of a SLAM-estimated one substantially affects the accuracy, creating a large gap between the reported results and the actual performance on real-world data.
title Volumetric Semantically Consistent 3D Panoptic Mapping
topic Robotics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2309.14737