The Hilti x Trimble
SLAM Challenge 2026

Live evaluation system

Although the 2026 edition of the SLAM Challenge has concluded, the evaluation system remains open for submissions. This allows teams to continue testing and refining their solutions against the benchmark and the other teams.

The challenge offers evaluation in two categories:

• SLAM: estimate the camera trajectory in your preferred reference system.
• Localization: estimate the camera trajectory within the floor plan reference frame, where the bottom-left pixel of the floor plan is considered to be the (0,0) coordinate.

Submissions are ranked based on trajectory completeness and position accuracy. Each pose is scored using an exponential accuracy model that heavily rewards precise localization: perfect poses receive full points, while larger errors contribute progressively fewer points. Each run yields a score between 0 and 100, and there are 25 (SLAM) / 24 (Localization) runs in total. The final score is the sum of all run scores. Please note that although 30 sequences are provided, the final score used for the leaderboard excludes runs for which ground truth data was originally provided for the participants of the challenge.

Visit the evaluation system

Citation

When using this work in an academic context, please cite in the following manner:

@misc{slamchallenge2026,
    title = {{Hilti}-{Trimble}-{Oxford} Dataset: 360 Visual-Inertial Benchmark with Floor Plan Priors for SLAM and Localization},
    author = {Centanni, Samuele and Zhang, Yuhao and Tao, Yifu and Kindle, Julien and Neuhaus, Frank and Koß, Tilman and Patel, Aryaman and Helmberger, Michael and Szymańska, Emilia and Gräber, Torben and Fallon, Maurice},
    year = {2026},
    eprint = {2607.06464},
    url = {https://arxiv.org/abs/2607.06464}
}

License

All datasets and benchmarks on this page are copyright by us and published under the Creative Commons Attribution NonCommercial ShareAlike 3.0 License. This means that you must attribute the work in the manner specified by the authors, you may not use this work for commercial purposes and if you alter, transform, or build upon this work, you may distribute the resulting work only under the same license.

Contact

Any dataset-related questions and concerns can be raised as issues at github.com/Hilti-Research/hilti-trimble-slam-challenge-2026/issues

Other queries - including about the webpage, the evaluation server operation or the conference workshop - should be forwarded to challenge@hilti.com