Benchmarking Egocentric Visual-Inertial SLAM at City Scale
This provides a crucial benchmark for researchers in wearable and robotics to evaluate SLAM systems under real-world egocentric challenges, though it is incremental as it focuses on dataset creation rather than algorithmic innovation.
The authors tackled the lack of realistic benchmarks for egocentric visual-inertial SLAM by introducing a new dataset with centimeter-accurate ground truth poses at city scale, showing that state-of-the-art systems fail under challenging conditions like night walking or vehicle travel.
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. The dataset and benchmark are available at https://www.lamaria.ethz.ch.