Saved in:
Bibliographic Details
Main Authors: Zhang, Boxuan, Kleeman, Lindsay, Burke, Michael
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2309.11698
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910696115011584
author Zhang, Boxuan
Kleeman, Lindsay
Burke, Michael
author_facet Zhang, Boxuan
Kleeman, Lindsay
Burke, Michael
contents Neural radiance fields (NeRFs) are a powerful tool for implicit scene representations, allowing for differentiable rendering and the ability to make predictions about unseen viewpoints. There has been growing interest in object and scene-based localisation using NeRFs, with a number of recent works relying on sampling-based or Monte-Carlo localisation schemes. Unfortunately, these can be extremely computationally expensive, requiring multiple network forward passes to infer camera or object pose. To alleviate this, a variety of sampling strategies have been applied, many relying on keypoint recognition techniques from classical computer vision. This work conducts a systematic empirical comparison of these approaches and shows that in contrast to conventional feature matching approaches for geometry-based localisation, sampling-based localisation using NeRFs benefits significantly from stable features. Results show that rendering stable features provides significantly better estimation with a tenfold reduction in the number of forward passes required.
format Preprint
id arxiv_https___arxiv_org_abs_2309_11698
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Rendering Stable Features Improves Sampling-Based Localisation with Neural Radiance Fields
Zhang, Boxuan
Kleeman, Lindsay
Burke, Michael
Robotics
Neural radiance fields (NeRFs) are a powerful tool for implicit scene representations, allowing for differentiable rendering and the ability to make predictions about unseen viewpoints. There has been growing interest in object and scene-based localisation using NeRFs, with a number of recent works relying on sampling-based or Monte-Carlo localisation schemes. Unfortunately, these can be extremely computationally expensive, requiring multiple network forward passes to infer camera or object pose. To alleviate this, a variety of sampling strategies have been applied, many relying on keypoint recognition techniques from classical computer vision. This work conducts a systematic empirical comparison of these approaches and shows that in contrast to conventional feature matching approaches for geometry-based localisation, sampling-based localisation using NeRFs benefits significantly from stable features. Results show that rendering stable features provides significantly better estimation with a tenfold reduction in the number of forward passes required.
title Rendering Stable Features Improves Sampling-Based Localisation with Neural Radiance Fields
topic Robotics
url https://arxiv.org/abs/2309.11698