UL-VIO: Ultra-lightweight Visual-Inertial Odometry with Noise Robust Test-time Adaptation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Park, Jinho, Chun, Se Young, Seok, Mingoo
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918395560067072
author Park, Jinho
Chun, Se Young
Seok, Mingoo
author_facet Park, Jinho
Chun, Se Young
Seok, Mingoo
contents Data-driven visual-inertial odometry (VIO) has received highlights for its performance since VIOs are a crucial compartment in autonomous robots. However, their deployment on resource-constrained devices is non-trivial since large network parameters should be accommodated in the device memory. Furthermore, these networks may risk failure post-deployment due to environmental distribution shifts at test time. In light of this, we propose UL-VIO -- an ultra-lightweight (<1M) VIO network capable of test-time adaptation (TTA) based on visual-inertial consistency. Specifically, we perform model compression to the network while preserving the low-level encoder part, including all BatchNorm parameters for resource-efficient test-time adaptation. It achieves 36X smaller network size than state-of-the-art with a minute increase in error -- 1% on the KITTI dataset. For test-time adaptation, we propose to use the inertia-referred network outputs as pseudo labels and update the BatchNorm parameter for lightweight yet effective adaptation. To the best of our knowledge, this is the first work to perform noise-robust TTA on VIO. Experimental results on the KITTI, EuRoC, and Marulan datasets demonstrate the effectiveness of our resource-efficient adaptation method under diverse TTA scenarios with dynamic domain shifts.
format Preprint
id arxiv_https___arxiv_org_abs_2409_13106
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle UL-VIO: Ultra-lightweight Visual-Inertial Odometry with Noise Robust Test-time Adaptation
Park, Jinho
Chun, Se Young
Seok, Mingoo
Computer Vision and Pattern Recognition
Data-driven visual-inertial odometry (VIO) has received highlights for its performance since VIOs are a crucial compartment in autonomous robots. However, their deployment on resource-constrained devices is non-trivial since large network parameters should be accommodated in the device memory. Furthermore, these networks may risk failure post-deployment due to environmental distribution shifts at test time. In light of this, we propose UL-VIO -- an ultra-lightweight (<1M) VIO network capable of test-time adaptation (TTA) based on visual-inertial consistency. Specifically, we perform model compression to the network while preserving the low-level encoder part, including all BatchNorm parameters for resource-efficient test-time adaptation. It achieves 36X smaller network size than state-of-the-art with a minute increase in error -- 1% on the KITTI dataset. For test-time adaptation, we propose to use the inertia-referred network outputs as pseudo labels and update the BatchNorm parameter for lightweight yet effective adaptation. To the best of our knowledge, this is the first work to perform noise-robust TTA on VIO. Experimental results on the KITTI, EuRoC, and Marulan datasets demonstrate the effectiveness of our resource-efficient adaptation method under diverse TTA scenarios with dynamic domain shifts.
title UL-VIO: Ultra-lightweight Visual-Inertial Odometry with Noise Robust Test-time Adaptation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2409.13106