Papers
arxiv:2410.00702

FlashMix: Fast Map-Free LiDAR Localization via Feature Mixing and Contrastive-Constrained Accelerated Training

Published on Sep 27, 2024
Authors:
,
,
,

Abstract

FlashMix enables fast and accurate LiDAR localization using a frozen backbone and MLP mixer with descriptor aggregation and metric learning regularization.

AI-generated summary

Map-free LiDAR localization systems accurately localize within known environments by predicting sensor position and orientation directly from raw point clouds, eliminating the need for large maps and descriptors. However, their long training times hinder rapid adaptation to new environments. To address this, we propose FlashMix, which uses a frozen, scene-agnostic backbone to extract local point descriptors, aggregated with an MLP mixer to predict sensor pose. A buffer of local descriptors is used to accelerate training by orders of magnitude, combined with metric learning or contrastive loss regularization of aggregated descriptors to improve performance and convergence. We evaluate FlashMix on various LiDAR localization benchmarks, examining different regularizations and aggregators, demonstrating its effectiveness for rapid and accurate LiDAR localization in real-world scenarios. The code is available at https://github.com/raktimgg/FlashMix.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2410.00702
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2410.00702 in a model README.md to link it from this page.

Datasets citing this paper 1

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2410.00702 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.