The LaMAria Dataset and Benchmark

Teaser

Benchmarking Egocentric Visual-Inertial SLAM at City Scale

Anusha Krishnan1*, Shaohui Liu1*, Paul-Edouard Sarlin2*, Oscar Gentilhomme1,
David Caruso3, Maurizio Monge3, Richard Newcombe3, Jakob Engel3, Marc Pollefeys1,4

* Equal contribution

1 ETH Zurich     2 Google     3 Meta Reality Labs Research    4 Microsoft Spatial AI Lab

ICCV 2025
Paper
Code

Abstract

Precise 6-DoF simultaneous localization and mapping (SLAM) from onboard sensors is critical for wearable devices capturing egocentric data, which exhibits specific challenges, such as a wider diversity of motions and viewpoints, prevalent dynamic visual content, or long sessions affected by time-varying sensor calibration. While recent progress on SLAM has been swift, academic research is still driven by benchmarks that do not reflect these challenges or do not offer sufficiently accurate ground truth poses. In this paper, we introduce a new dataset and benchmark for visual-inertial SLAM with egocentric, multi-modal data. We record hours and kilometers of trajectories through a city center with glasses-like devices equipped with various sensors. We leverage surveying tools to obtain control points as indirect pose annotations that are metric, centimeter-accurate, and available at city scale. This makes it possible to evaluate extreme trajectories that involve walking at night or traveling in a vehicle. We show that state-of-the-art systems developed by academia are not robust to these challenges and we identify components that are responsible for this. In addition, we design tracks with different levels of difficulty to ease in-depth analysis and evaluation of less mature approaches.

Overview

Control Points
Trajectories
Trajectories
Control Points

BibTeX

@InProceedings{Krishnan_2025_ICCV,
  author    = {Krishnan, Anusha and
               Liu, Shaohui and
               Sarlin, Paul-Edouard and
               Gentilhomme, Oscar and
               Caruso, David and
               Monge, Maurizio and
               Newcombe, Richard and
               Engel, Jakob and
               Pollefeys, Marc},
  title     = {Benchmarking Egocentric Visual-Inertial SLAM at City Scale},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
  year      = {2025}
}