The TUM VI Benchmark for Evaluating Visual-Inertial Odometry

TL;DR

The TUM VI benchmark provides a comprehensive, high-resolution dataset with synchronized visual and inertial data for evaluating and advancing visual-inertial odometry methods in diverse scenes.

Contribution

It introduces a new, publicly available dataset with high-quality, synchronized visual-inertial data and ground truth for benchmarking VI odometry algorithms.

Findings

State-of-the-art VI methods evaluated on the dataset.

Dataset includes diverse scenes and high-resolution data.

Provides accurate pose ground truth for benchmarking.

Abstract

Visual odometry and SLAM methods have a large variety of applications in domains such as augmented reality or robotics. Complementing vision sensors with inertial measurements tremendously improves tracking accuracy and robustness, and thus has spawned large interest in the development of visual-inertial (VI) odometry approaches. In this paper, we propose the TUM VI benchmark, a novel dataset with a diverse set of sequences in different scenes for evaluating VI odometry. It provides camera images with 1024x1024 resolution at 20 Hz, high dynamic range and photometric calibration. An IMU measures accelerations and angular velocities on 3 axes at 200 Hz, while the cameras and IMU sensors are time-synchronized in hardware. For trajectory evaluation, we also provide accurate pose ground truth from a motion capture system at high frequency (120 Hz) at the start and end of the sequences which we accurately aligned with the camera and IMU measurements. The full dataset with raw and calibrated data is publicly available. We also evaluate state-of-the-art VI odometry approaches on our dataset.