Fast Global Localization on Neural Radiance Field

TL;DR

Fast Loc-NeRF introduces a multi-resolution, coarse-to-fine approach combined with particle rejection weighting to significantly improve the efficiency and accuracy of global localization in NeRF-based maps.

Contribution

It presents Fast Loc-NeRF, a novel method that accelerates NeRF-based localization using multi-resolution matching and uncertainty-based particle rejection.

Findings

Sets new state-of-the-art localization accuracy on benchmarks.

Achieves faster localization with reduced computational cost.

Maintains high precision despite efficiency improvements.

Abstract

Neural Radiance Fields (NeRF) presented a novel way to represent scenes, allowing for high-quality 3D reconstruction from 2D images. Following its remarkable achievements, global localization within NeRF maps is an essential task for enabling a wide range of applications. Recently, Loc-NeRF demonstrated a localization approach that combines traditional Monte Carlo Localization with NeRF, showing promising results for using NeRF as an environment map. However, despite its advancements, Loc-NeRF encounters the challenge of a time-intensive ray rendering process, which can be a significant limitation in practical applications. To address this issue, we introduce Fast Loc-NeRF, which leverages a coarse-to-fine approach to enable more efficient and accurate NeRF map-based global localization. Specifically, Fast Loc-NeRF matches rendered pixels and observed images on a multi-resolution from low to high resolution. As a result, it speeds up the costly particle update process while maintaining precise localization results. Additionally, to reject the abnormal particles, we propose particle rejection weighting, which estimates the uncertainty of particles by exploiting NeRF's characteristics and considers them in the particle weighting process. Our Fast Loc-NeRF sets new state-of-the-art localization performances on several benchmarks, convincing its accuracy and efficiency.