# Hilti-Oxford Dataset: A Millimetre-Accurate Benchmark for Simultaneous Localization and Mapping

arXiv: https://arxiv.org/abs/2208.09825 · HTML: https://mlsanity.com/paper/2208.09825/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Aug 2022.

## Built on by (most cited first, 23 of 23)

- [FAST-LIVO2: Fast, Direct LiDAR-Inertial-Visual Odometry](https://mlsanity.com/paper/2408.14035/) (2024)
- [MCD: Diverse Large-Scale Multi-Campus Dataset for Robot Perception](https://mlsanity.com/paper/2403.11496/) (2024)
- [VBR: A Vision Benchmark in Rome](https://mlsanity.com/paper/2404.11322/) (2024)
- [Benchmarking Egocentric Visual-Inertial SLAM at City Scale](https://mlsanity.com/paper/2509.26639/) (2025)
- [DUFOMap: Efficient Dynamic Awareness Mapping](https://mlsanity.com/paper/2403.01449/) (2024)
- [The Monado SLAM Dataset for Egocentric Visual-Inertial Tracking](https://mlsanity.com/paper/2508.00088/) (2025)
- [Seeing in the Dark: Benchmarking Egocentric 3D Vision with the Oxford Day-and-Night Dataset](https://mlsanity.com/paper/2506.04224/) (2025)
- [S-Graphs 2.0 -- A Hierarchical-Semantic Optimization and Loop Closure for SLAM](https://mlsanity.com/paper/2502.18044/) (2025)
- [VSLAM-LAB: A Comprehensive Framework for Visual SLAM Methods and Datasets](https://mlsanity.com/paper/2504.04457/) (2025)
- [InCrowd-VI: A Realistic Visual-Inertial Dataset for Evaluating SLAM in Indoor Pedestrian-Rich Spaces for Human Navigation](https://mlsanity.com/paper/2411.14358/) (2024)
- [Traj-LIO: A Resilient Multi-LiDAR Multi-IMU State Estimator Through Sparse Gaussian Process](https://mlsanity.com/paper/2402.09189/) (2024)
- [SLAM for Indoor Mapping of Wide Area Construction Environments](https://mlsanity.com/paper/2404.17215/) (2024)
- [Empir3D : A Framework for Multi-Dimensional Point Cloud Assessment](https://mlsanity.com/paper/2306.03660/) (2023)
- [CULTURE3D: A Large-Scale and Diverse Dataset of Cultural Landmarks and Terrains for Gaussian-Based Scene Rendering](https://mlsanity.com/paper/2501.06927/) (2025)
- [An RTK-SLAM Dataset for Absolute Accuracy Evaluation in GNSS-Degraded Environments](https://mlsanity.com/paper/2604.07151/) (2026)
- [Structured-Li-GS: Structured 3D Gaussians Splatting with LiDAR Incorporation and Spatial Constraints](https://mlsanity.com/paper/2606.27509/) (2026)
- [Feature Tracks are not Zero-Mean Gaussian](https://mlsanity.com/paper/2303.14315/) (2023)
- [An Efficient Plane Extraction Approach for Bundle Adjustment on LiDAR Point clouds](https://mlsanity.com/paper/2305.00287/) (2023)
- [RMS: Redundancy-Minimizing Point Cloud Sampling for Real-Time Pose Estimation](https://mlsanity.com/paper/2312.07337/) (2023)
- [DynamicGlue: Epipolar and Time-Informed Data Association in Dynamic Environments using Graph Neural Networks](https://mlsanity.com/paper/2403.11370/) (2024)
- [Diffusion Based Robust LiDAR Place Recognition](https://mlsanity.com/paper/2504.12412/) (2025)
- [Multi-LVI-SAM: A Robust LiDAR-Visual-Inertial Odometry for Multiple Fisheye Cameras](https://mlsanity.com/paper/2509.05740/) (2025)
- [MIRAGE: Metric Inference and Reliability-Aware Gaussian Estimation from Feed-Forward Vision](https://mlsanity.com/paper/2610.12568/) (2026)

## Abstract (arXiv)

Simultaneous Localization and Mapping (SLAM) is being deployed in real-world applications, however many state-of-the-art solutions still struggle in many common scenarios. A key necessity in progressing SLAM research is the availability of high-quality datasets and fair and transparent benchmarking. To this end, we have created the Hilti-Oxford Dataset, to push state-of-the-art SLAM systems to their limits. The dataset has a variety of challenges ranging from sparse and regular construction sites to a 17th century neoclassical building with fine details and curved surfaces. To encourage multi-modal SLAM approaches, we designed a data collection platform featuring a lidar, five cameras, and an IMU (Inertial Measurement Unit). With the goal of benchmarking SLAM algorithms for tasks where accuracy and robustness are paramount, we implemented a novel ground truth collection method that enables our dataset to accurately measure SLAM pose errors with millimeter accuracy. To further ensure accuracy, the extrinsics of our platform were verified with a micrometer-accurate scanner, and temporal calibration was managed online using hardware time synchronization. The multi-modality and diversity of our dataset attracted a large field of academic and industrial researchers to enter the second edition of the Hilti SLAM challenge, which concluded in June 2022. The results of the challenge show that while the top three teams could achieve an accuracy of 2cm or better for some sequences, the performance dropped off in more difficult sequences.