Saved in:
Bibliographic Details
Main Authors: Xue, Shangjie, Dill, Jesse, Mathur, Pranay, Dellaert, Frank, Tsiotras, Panagiotis, Xu, Danfei
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.06948
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910488640618496
author Xue, Shangjie
Dill, Jesse
Mathur, Pranay
Dellaert, Frank
Tsiotras, Panagiotis
Xu, Danfei
author_facet Xue, Shangjie
Dill, Jesse
Mathur, Pranay
Dellaert, Frank
Tsiotras, Panagiotis
Xu, Danfei
contents This paper presents Neural Visibility Field (NVF), a novel uncertainty quantification method for Neural Radiance Fields (NeRF) applied to active mapping. Our key insight is that regions not visible in the training views lead to inherently unreliable color predictions by NeRF at this region, resulting in increased uncertainty in the synthesized views. To address this, we propose to use Bayesian Networks to composite position-based field uncertainty into ray-based uncertainty in camera observations. Consequently, NVF naturally assigns higher uncertainty to unobserved regions, aiding robots to select the most informative next viewpoints. Extensive evaluations show that NVF excels not only in uncertainty quantification but also in scene reconstruction for active mapping, outperforming existing methods.
format Preprint
id arxiv_https___arxiv_org_abs_2406_06948
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Neural Visibility Field for Uncertainty-Driven Active Mapping
Xue, Shangjie
Dill, Jesse
Mathur, Pranay
Dellaert, Frank
Tsiotras, Panagiotis
Xu, Danfei
Computer Vision and Pattern Recognition
Robotics
This paper presents Neural Visibility Field (NVF), a novel uncertainty quantification method for Neural Radiance Fields (NeRF) applied to active mapping. Our key insight is that regions not visible in the training views lead to inherently unreliable color predictions by NeRF at this region, resulting in increased uncertainty in the synthesized views. To address this, we propose to use Bayesian Networks to composite position-based field uncertainty into ray-based uncertainty in camera observations. Consequently, NVF naturally assigns higher uncertainty to unobserved regions, aiding robots to select the most informative next viewpoints. Extensive evaluations show that NVF excels not only in uncertainty quantification but also in scene reconstruction for active mapping, outperforming existing methods.
title Neural Visibility Field for Uncertainty-Driven Active Mapping
topic Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2406.06948