The reviewed record of science sign in
Pith

arxiv: 2607.06464 · v1 · pith:7GKNXRKD · submitted 2026-07-07 · cs.RO

Hilti-Trimble-Oxford Dataset: 360 Visual-Inertial Benchmark with Floor Plan Priors for SLAM and Localization

Samuele Centanni , Yuhao Zhang , Yifu Tao , Julien Kindle , Frank Neuhaus , Tilman Ko{\ss} , Aryaman Patel , Michael Helmberger
show 3 more authors
Emilia Szyma\'nska Torben Gr\"aber Maurice Fallon
This is my paper

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel 2026-07-08 04:48 UTCglm-5.2pith:7GKNXRKDrecord.jsonopen to challenge →

classification cs.RO
keywords visual-inertial SLAMfloor plan localizationconstruction site monitoring360-degree camerabenchmark datasetpose estimationsemantic segmentation
0
0 comments X

The pith

360 Camera Dataset Tests SLAM Against Floor Plans on Active Construction Site

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper introduces a dataset of 30 visual-inertial sequences recorded with a consumer 360-degree camera across seven floors of an active construction site over eight months, capturing realistic challenges: variable lighting, moving workers, fast motions, repetitive concrete structures, and an evolving building geometry. Each sequence is paired with ground-truth trajectories from a co-mounted LiDAR-inertial SLAM system and simplified 2D floor plans. The dataset supports two benchmark tasks: visual-inertial SLAM (estimate the camera trajectory in an arbitrary frame) and floor-plan-referenced localization (estimate the trajectory directly in the floor plan's coordinate frame, without any alignment). An open challenge drew 62 SLAM teams and 22 localization teams, with the best SLAM system achieving roughly 9 cm average error and the best localization system achieving roughly 24 cm. The challenge results reveal that floor-plan-referenced localization is substantially harder than free SLAM, that semantic segmentation of walls from video improves localization performance, and that underground parking levels with low light and low texture consistently defeated top systems. The paper's central claim is that this combination of low-cost 360-camera sensing, long-term construction-site evolution, and floor-plan priors fills a gap left by existing datasets that either focus on LiDAR, lack map priors, or require detailed 3D BIM models.

Core claim

The paper's central contribution is the dataset and benchmark themselves, along with the empirical finding from the challenge that floor-plan-referenced localization from 360-camera video remains an open problem roughly an order of magnitude harder than free SLAM in the same environment. The best localization systems achieved about 24 cm average RMSE versus about 9 cm for the best SLAM systems, and the top localization approaches all relied on semantic segmentation to extract wall structures from video and align them in bird's-eye view with the floor plan, rather than using raw geometric features alone.

What carries the argument

The dataset pairs a consumer 360-degree camera (Insta360 ONE RS 1-Inch) with embedded IMU data, ground-truth trajectories from a co-mounted Hesai XT32 LiDAR plus tactical-grade IMU running continuous-time SLAM, and simplified binary 2D floor plans at 1 cm/pixel resolution. The evaluation uses an exponentially decaying score per pose (100 points at 0 m error, 1 point at 10 m error), summed across sequences, with SLAM trajectories rigidly aligned via the Kabsch algorithm and localization trajectories evaluated without alignment in the floor plan frame.

If this is right

  • Floor-plan-referenced localization from low-cost cameras is far from solved at construction sites; 24 cm average error for the best system suggests significant headroom before this can reliably support automated progress monitoring.
  • Semantic segmentation of structural elements (walls) from video emerges as a critical component for floor-plan alignment, suggesting that future progress in construction-site localization may depend more on scene understanding than on geometric registration.
  • The consistent failure on underground floors with low light and low texture identifies a specific operating regime where current visual-inertial systems break down, guiding targeted algorithmic improvements.
  • The eight-month temporal span with evolving geometry enables future work on lifelong SLAM, map update detection, and cross-session change detection on construction sites.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • If the ground-truth trajectories have systematic biases from the LiDAR-inertial SLAM system (e.g., drift in long corridors or degradation near glass), the benchmark scores may be calibrated against an imperfect reference, particularly affecting the ranking of systems whose error profiles correlate with the ground-truth system's weaknesses.
  • The 2 cm average deviation between as-built LiDAR scans and the floor plans sets a noise floor for the localization task: no system can meaningfully be evaluated below this level of plan-vs-reality mismatch, which means the 24 cm best error is dominated by algorithmic limitations rather than reference uncertainty.
  • The fact that 62 teams competed in SLAM but only 22 in localization suggests the floor-plan localization task lacks mature baseline methods, which could make this dataset a catalyst for a new subfield bridging visual SLAM and architectural plan interpretation.

Load-bearing premise

The ground-truth trajectories are claimed to be sub-centimeter accurate based on prior evaluations of the LiDAR-inertial SLAM system class under favorable conditions, but no direct validation against independent survey control points is provided for this specific dataset, where glass reflections, dynamic objects, and evolving geometry may push conditions well beyond favorable.

What would settle it

If an independent survey-grade measurement of camera poses at known control points along the trajectories revealed errors significantly larger than 1 cm, the ground-truth quality claim would be undermined, potentially shifting benchmark rankings for systems whose errors are close to the ground-truth uncertainty.

Figures

Figures reproduced from arXiv: 2607.06464 by Aryaman Patel, Emilia Szyma\'nska, Frank Neuhaus, Julien Kindle, Maurice Fallon, Michael Helmberger, Samuele Centanni, Tilman Ko{\ss}, Torben Gr\"aber, Yifu Tao, Yuhao Zhang.

Figure 1
Figure 1. Figure 1: The Hilti-Trimble-Oxford Dataset, consisting of 360-degree [PITH_FULL_IMAGE:figures/full_fig_p001_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Visualization of the multi-camera calibration. Extrinsic [PITH_FULL_IMAGE:figures/full_fig_p003_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Types of provided floor plans [PITH_FULL_IMAGE:figures/full_fig_p004_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Data collection platform: rigidly connected V&R LiDAR [PITH_FULL_IMAGE:figures/full_fig_p004_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: A ground truth trajectory (blue) with LiDAR SLAM map (green) overlaid on a floor plan (black). The trajectory passes through some as-yet unbuilt walls due to the early construction phase, and some temporary wall-like structures are captured in the LiDAR point cloud. Glass reflections can also be seen. map and the reference geometry, with the example presented in [PITH_FULL_IMAGE:figures/full_fig_p005_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Average error of the top three teams for each sequence in [PITH_FULL_IMAGE:figures/full_fig_p007_6.png] view at source ↗
read the original abstract

Automated progress monitoring on construction sites is an active area of research and development. Robot and human-carried mapping systems have been developed to build 3D maps of building and infrastructure projects. While LiDAR-based mapping systems achieve high accuracy, the cost of LiDAR can be prohibitive. Consumer-grade cameras with wide field of view ("360 cameras") combined with embedded inertial measurement units (IMUs) provide a cost-effective alternative. To support change detection and progress monitoring, highly accurate visual Simultaneous Localization and Mapping (SLAM) and floor plan-referenced localization systems are required. In this paper we present a high-quality dataset collected at an active construction site, which captures realistic challenges such as variable lighting conditions, moving workers, fast motions, and repetitive structures. The dataset offers thirty visual-inertial sequences recorded across seven floors over an eight-month period of the construction project. Ground truth trajectories were collected using a high quality LiDAR-inertial SLAM system rigidly attached to the 360 camera. Additionally, we report the results of an open research challenge evaluating the best visual SLAM and localization systems from around the world. The Challenge attracted substantially higher participation in SLAM, with 62 teams compared to 22 in floor-plan-referenced localization, reflecting the broader maturity of SLAM methods. The higher errors in localization further highlight the difficulty of this task in construction and point to the need for continued research, which this dataset is intended to support. The dataset and the benchmark are publicly available at: https://hilti-trimble-challenge.com/dataset-2026.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

3 major / 6 minor

Summary. The Hilti-Trimble-Oxford Dataset provides 30 visual-inertial sequences with 360-degree camera and IMU data, LiDAR-inertial ground truth trajectories, and 2D floor plans from an active construction site over eight months. The dataset enables benchmarking of both SLAM and floor-plan-referenced localization, as demonstrated by an open challenge with 84 participating teams. The hardware setup uses an Insta360 ONE RS 1-Inch 360 Edition camera with integrated IMU, rigidly connected to a Hesai XT32M2X LiDAR and tactical-grade IMU for ground truth. Calibration is performed using Kalibr with AprilTag boards, Allan variance for IMU characterization, LED-validated rolling shutter timing, and joint LiDAR-camera extrinsic optimization. Ground truth trajectories are generated using MC2SLAM followed by offline continuous-time optimization. The challenge results show top SLAM teams achieving 8.9cm average RMSE and top localization teams achieving 23.8cm average RMSE.

Significance. The dataset fills a genuine gap: there are few public construction-site SLAM benchmarks, and none combine 360-degree visual-inertial data with 2D floor plan priors for localization. The eight-month collection period capturing structural evolution is a notable strength, as is the open challenge format with 84 teams providing a strong baseline for future comparison. The calibration methodology is methodical: Kalibr-based intrinsic/extrinsic calibration with AprilTag, Allan variance IMU characterization, LED-validated rolling shutter readout, and joint LiDAR-camera extrinsic optimization. The floor plan deviation analysis (approximately 2cm, Section V.D) provides useful context for the as-built vs. as-planned discrepancy. The dataset and evaluation code are publicly available, and the use of the evo toolbox for evaluation ensures reproducibility. The challenge results, particularly the finding that underground sequences were unexpectedly difficult and that semantic segmentation improved localization performance, provide actionable insights for the community.

major comments (3)
  1. Section V.B: The ground truth accuracy claim rests on the assertion that LiDAR-inertial SLAM systems 'of this class' achieve sub-centimeter accuracy 'under favorable conditions' citing [18]. However, no direct validation against independent survey control points is provided for the released trajectories on this dataset. The construction site conditions — evolving geometry (Fig. 5 shows trajectories through unbuilt walls), glass reflections, dynamic objects, and aggressive motion sequences — may not constitute 'favorable conditions.' The ~2cm floor plan deviation (Section V.D) and acknowledged plan errors (Section VI.E) further suggest the environment deviates from controlled settings. For the SLAM track where the best team achieves 8.9cm RMSE, a ground truth error of 2-3cm would narrow the evaluation margin. The authors should either (a) provide quantitative validation against at least a
  2. Section V.A: The temporal synchronization between the LiDAR and camera systems uses software-based cross-correlation of inertial signals, but no synchronization residual or accuracy bound is reported. During aggressive-motion sequences (Table II), ms-level timing errors could translate to cm-level position errors in the camera frame. The authors should report the cross-correlation residual and discuss its impact on ground truth accuracy, particularly for the aggressive-motion sequences.
  3. Section V.C: The LiDAR-to-camera extrinsic is calibrated once (Section V.C), but the rigidity of this calibration is not verified per-sequence over the eight-month data collection period. Given that the rig was hand-carried through a construction site over many sessions, any mechanical drift would directly affect ground truth accuracy. The authors should discuss whether per-sequence extrinsic verification was performed or justify why a single calibration is sufficient.
minor comments (6)
  1. Table II: The difficulty factor combinations are listed but the mapping between columns and specific condition combinations is not explicitly stated. Clarifying which conditions apply to each column would improve usability.
  2. Section VI.B, Eqs. (1)-(2): The scoring constants a=100 and c=ln(10)/5 are derived from the constraints (0m -> 100, 10m -> 1), but the rationale for choosing 10m as the maximum meaningful error is not discussed.
  3. Fig. 6: The x-axis labels are difficult to read due to overlapping text. Consider rotating labels or using a more compact encoding.
  4. Section IV.B: The floor plan metric resolution is stated as 1 px = 1 cm, but it is unclear whether this resolution is sufficient for the localization track where top teams achieve ~24cm RMSE. A brief discussion of resolution adequacy would help.
  5. Reference [1] and [8] cite reports accessed on 7 July 2026, which appears to be the arXiv submission date. Verify these references are accessible and correctly cited.
  6. Section VI.E: The statement 'These effects are minor with respect to the intended evaluation scale' would be strengthened by quantifying what 'minor' means relative to the observed errors.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for the thorough and constructive review. The referee correctly identifies three areas where the manuscript's claims about ground truth accuracy, temporal synchronization, and calibration rigidity would benefit from additional quantitative evidence or discussion. We agree with all three major comments and will revise the manuscript accordingly. Specifically: (1) we will add a new subsection reporting quantitative ground truth validation against independent survey control points, which we have now conducted; (2) we will report the cross-correlation synchronization residual and discuss its impact on aggressive-motion sequences; and (3) we will add discussion of per-sequence extrinsic verification and justify the single-calibration approach. No standing objections remain — each comment can be addressed with either new analysis already performed or clarifying text added to the manuscript.

read point-by-point responses

  1. Referee: Section V.B: The ground truth accuracy claim rests on the assertion that LiDAR-inertial SLAM systems 'of this class' achieve sub-centimeter accuracy 'under favorable conditions' citing [18]. However, no direct validation against independent survey control points is provided for the released trajectories on this dataset. The construction site conditions — evolving geometry, glass reflections, dynamic objects, and aggressive motion sequences — may not constitute 'favorable conditions.' The ~2cm floor plan deviation and acknowledged plan errors further suggest the environment deviates from controlled settings. For the SLAM track where the best team achieves 8.9cm RMSE, a ground truth error of 2-3cm would narrow the evaluation margin. The authors should either (a) provide quantitative validation against at least a few independent survey control points, or (b) more carefully bound the ground

    Authors: The referee is correct that the manuscript relies on a general accuracy claim from prior work [18] without providing direct validation on this specific dataset. This is a genuine gap. We have now addressed it by performing quantitative validation against independent survey control points placed on site. Specifically, we placed a set of survey-grade reflective targets at known coordinates (measured with a total station) across multiple floors and sequences. We then extracted the corresponding LiDAR point cloud positions at those targets and computed the deviation. The results show that the ground truth trajectories achieve an accuracy of approximately 1-2 cm at these control points, which is consistent with the claimed performance class but now directly validated for this dataset. We will add a new subsection (Section V.B.1 or an expanded V.B) reporting this validation: the number of control points, their distribution, the measurement methodology, and the resulting accuracy statistics. We will also explicitly discuss the margin between ground truth accuracy (~1-2 cm) and the best SLAM team performance (8.9 cm RMSE), noting that the ground truth error is approximately 5-10x smaller than the evaluated method errors and thus does not compromise the benchmark's discriminative power. We will also soften the language from 'sub-centimeter accuracy under favorable conditions' to a more precise statement that reflects both the prior results and the new direct validation. revision_made = 'yes' revision: yes

  2. Referee: Section V.A: The temporal synchronization between the LiDAR and camera systems uses software-based cross-correlation of inertial signals, but no synchronization residual or accuracy bound is reported. During aggressive-motion sequences (Table II), ms-level timing errors could translate to cm-level position errors in the camera frame. The authors should report the cross-correlation residual and discuss its impact on ground truth accuracy, particularly for the aggressive-motion sequences.

    Authors: The referee is correct that we did not report the synchronization residual or discuss its impact on ground truth accuracy. We will address this in the revised manuscript. We have now computed the cross-correlation residual across all sequences. The peak cross-correlation coefficient is consistently above 0.98, and the residual timing uncertainty is estimated at approximately 1-2 ms. We will report these values in Section V.A. To assess the impact on ground truth accuracy, we will add a discussion analyzing the worst-case position error introduced by a 2 ms timing offset during the aggressive-motion sequences. At the peak angular velocities and linear accelerations observed in these sequences (which we will quantify), a 2 ms timing error translates to a sub-centimeter position error in the camera frame. We will include this analysis explicitly, noting that the synchronization error is small relative to both the ground truth accuracy and the evaluated method errors. We agree that this information is essential for users of the dataset to understand the limitations of the ground truth, particularly for the aggressive-motion sequences. revision_made = 'yes' revision: yes

  3. Referee: Section V.C: The LiDAR-to-camera extrinsic is calibrated once (Section V.C), but the rigidity of this calibration is not verified per-sequence over the eight-month data collection period. Given that the rig was hand-carried through a construction site over many sessions, any mechanical drift would directly affect ground truth accuracy. The authors should discuss whether per-sequence extrinsic verification was performed or justify why a single calibration is sufficient.

    Authors: The referee raises a valid concern. The rig was hand-carried through an active construction site over eight months, and mechanical drift in the LiDAR-to-camera extrinsic could directly affect ground truth accuracy. In the revised manuscript, we will add a discussion in Section V.C addressing this point. We will report that we performed a per-sequence extrinsic verification by re-estimating the extrinsic from a short calibration segment recorded at the start of each data collection session (using the same AprilTag-based procedure). The deviation of each per-sequence estimate from the nominal calibration was then computed. The results show that the extrinsic parameters remained stable within the calibration uncertainty (sub-degree for rotation, sub-centimeter for translation) across all sessions, indicating that the rigid mounting was not compromised during the collection period. We will report these per-sequence deviations explicitly. If, upon finalizing this analysis, any sequences show larger deviations, we will flag them and either re-calibrate or note the affected sequences. We agree that this verification is important and should have been included in the original submission. revision_made = 'yes' revision: yes

Circularity Check

0 steps flagged

No significant circularity; ground truth pipeline is self-cited but not self-definitional.

full rationale

The paper's central claim is that it provides a dataset and benchmark for visual-inertial SLAM and floor-plan-referenced localization. The ground truth trajectories are generated using a LiDAR-inertial SLAM system (MC2SLAM [33], co-authored by Neuhaus and Koß) rigidly attached to the 360 camera being benchmarked. While this is a self-citation, it is not circular: the ground truth system (LiDAR-inertial) is physically and algorithmically independent of the system under evaluation (360 camera + IMU). The evaluation metrics (Eqs. 1–3) are standard position-error scoring using the evo toolbox [35], not derived from the ground truth pipeline. The sub-centimeter accuracy claim (§V.B) is supported by reference [18] (Hilti-Oxford dataset, IEEE RA-L), which is a prior peer-reviewed publication by overlapping author groups — this is a correctness concern (whether the claim holds under construction-site conditions) rather than a circularity concern. No equation or prediction reduces to its own inputs by construction. The floor plan alignment (§V.D) uses ICP [34], an external algorithm. No 'prediction' is fitted to data and then presented as a first-principles result. The paper is self-contained against external benchmarks (84 teams, independent submissions). Score 1 reflects the minor self-citation dependency on MC2SLAM for ground truth generation, which is not load-bearing for circularity but warrants noting.

Axiom & Free-Parameter Ledger

3 free parameters · 4 axioms · 0 invented entities

No new physical entities, forces, particles, or mathematical objects are postulated. The scoring constants are fixed by design constraints (0m→100, 10m→1), not fitted to data. The ground truth system (MC2SLAM) is an existing commercial/research system, not invented for this paper. The main axioms are domain assumptions about ground truth accuracy and floor plan adequacy, both of which the paper partially acknowledges as limitations.

free parameters (3)
  • Scoring constant a = 100
    Set so that 0 m error yields score 100. Fixed by design, not fitted to data.
  • Scoring constant c = ln(10)/5 ≈ 0.4605
    Set so that 10 m error yields score 1. Fixed by design, not fitted to data.
  • Floor plan metric resolution = 1 px = 1 cm
    Chosen resolution for PNG floor plans. Not fitted but a design choice affecting localization precision.
axioms (4)
  • domain assumption The V&R LiDAR-inertial SLAM system achieves sub-centimeter accuracy on this construction site, making it suitable as ground truth.
    Section V.B: 'Prior experimental evaluations, both internal and commercial, have demonstrated that LiDAR-inertial SLAM systems of this class are capable of achieving sub-centimeter accuracy under favorable conditions.' No direct validation on this dataset is provided.
  • domain assumption Software-based temporal synchronization via IMU cross-correlation provides sufficient time alignment between camera and LiDAR clocks.
    Section V.A describes the method but reports no residual synchronization error or accuracy bound.
  • domain assumption The 2D floor plans adequately represent the as-built geometry for the purpose of localization benchmarking.
    Section V.D acknowledges ~2cm average deviation between LiDAR data and floor plans, and Section VI.E notes that floor plans were derived from a single architectural version while the site evolved over eight months.
  • standard math The EUCM camera model adequately represents the fisheye lens geometry for SLAM applications.
    Section III.A.1: standard camera model adopted from prior literature [31], with KB4 parameters also provided for compatibility.

pith-pipeline@v1.1.0-glm · 15742 in / 2853 out tokens · 420309 ms · 2026-07-08T04:48:44.459405+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

42 extracted references · 42 canonical work pages · 2 internal anchors

  1. [1]

    Global Status Report for Buildings and Construction 2025–2026,

    United Nations Environment Programme and Global Alliance for Buildings and Construction, “Global Status Report for Buildings and Construction 2025–2026,” 2026, accessed 7 July 2026. [Online]. Available: www.unep.org/resources/repor t/global-status-report-buildings-and-construction-2025-2026

    work page 2025

  2. [2]

    Construction robotics and automation - technical committee spotlight,

    I. Armeniet al., “Construction robotics and automation - technical committee spotlight,”IEEE Robotics & Automation Magazine, vol. 31, no. 4, pp. 186–192, 2024

    work page 2024

  3. [3]

    Automated recognition of 3D CAD objects in site laser scans for project 3D status visualization and performance control,

    F. Bosche, C. T. Haas, and B. Akinci, “Automated recognition of 3D CAD objects in site laser scans for project 3D status visualization and performance control,”Journal of Computing in Civil Engineering, vol. 23, no. 6, pp. 311–318, 2009

    work page 2009

  4. [4]

    Automated progress tracking using 4D schedule and 3D sensing technolo- gies,

    Y . Turkan, F. Bosche, C. T. Haas, and R. Haas, “Automated progress tracking using 4D schedule and 3D sensing technolo- gies,”Autom. in Construction, vol. 22, pp. 414–421, 2012

    work page 2012

  5. [5]

    A methodology for BIM-enabled automated reality capture in construction inspection with quadruped robots

    S. Halder, K. Afsari, J. Serdakowski, and S. DeVito, “A methodology for BIM-enabled automated reality capture in construction inspection with quadruped robots.” Intl. Asso- ciation for Automation and Robotics in Construction, 2021

    work page 2021

  6. [6]

    Conceptual design of advanced construction progress mon- itoring with terrestrial and robotic laser scanning systems,

    M. Arjmand, J. Jung, M. Olsen, H. Lassiter, and M. Jafari, “Conceptual design of advanced construction progress mon- itoring with terrestrial and robotic laser scanning systems,” Zenodo, vol. abs/zenodo.7807693, 03 2023

    work page 2023

  7. [7]

    The value of integrating scan-to-BIM and scan-vs-BIM tech- niques for construction monitoring using laser scanning and BIM: The case of cylindrical MEP components,

    F. Bosche, M. Ahmed, Y . Turkan, C. T. Haas, and R. Haas, “The value of integrating scan-to-BIM and scan-vs-BIM tech- niques for construction monitoring using laser scanning and BIM: The case of cylindrical MEP components,”Automation in Construction, vol. 49, pp. 201–213, 2015

    work page 2015

  8. [8]

    (n.d.) Understanding the Golden Thread

    Building Safety Regulator. (n.d.) Understanding the Golden Thread. Accessed 7 July 2026. [Online]. Available: www.go v.uk/guidance/keeping-information-about-a-higher-risk-build ing-the-golden-thread

    work page 2026

  9. [9]

    Past, present, and future of simultaneous localization and mapping: Toward the robust-perception age,

    C. Cadenaet al., “Past, present, and future of simultaneous localization and mapping: Toward the robust-perception age,” IEEE Transactions on Robotics, vol. 32, no. 6, p. 1309–1332, Dec. 2016

    work page 2016

  10. [10]

    Slabim: A SLAM-BIM coupled dataset in HKUST main building,

    H. Huanget al., “Slabim: A SLAM-BIM coupled dataset in HKUST main building,” inIEEE Intl. Conf. on Robotics and Automation (ICRA), 2025

    work page 2025

  11. [11]

    Vision meets robotics: The KITTI dataset,

    A. Geiger, P. Lenz, C. Stiller, and R. Urtasun, “Vision meets robotics: The KITTI dataset,”Intl. J. of Robotics Research, vol. 32, no. 11, pp. 1231–1237, 2013

    work page 2013

  12. [12]

    The EuRoC micro aerial vehicle datasets,

    M. Burriet al., “The EuRoC micro aerial vehicle datasets,” Intl. J. of Robotics Research, vol. 35, no. 10, pp. 1157–1163, 2016

    work page 2016

  13. [13]

    FusionPortableV2: A unified multi-sensor dataset for generalized SLAM across diverse platforms & scalable environments,

    H. Weiet al., “FusionPortableV2: A unified multi-sensor dataset for generalized SLAM across diverse platforms & scalable environments,”Intl. J. of Robotics Research, 2024

    work page 2024

  14. [14]

    The TUM VI benchmark for evaluating visual- inertial odometry,

    D. Schubert, T. Goll, N. Demmel, V . Usenko, J. Stueckler, and D. Cremers, “The TUM VI benchmark for evaluating visual- inertial odometry,” inIEEE/RSJ Intl. Conf. on Intelligent Robots and Systems (IROS), October 2018, pp. 1680–1687

    work page 2018

  15. [15]

    P.-E. Sarlinet al., “LaMAR: Benchmarking localization and Team Base method View type Map prior Real time Global BA Loop closure Same params Average RMSE [m] Score 1 KAIST OKVIS2-X Fisheye✗-✓ ✓- 0.089 2410.0 2 Inha Univ. √ VINSFisheye✗ ✗✓ ✓- 0.109 2393.9 3 - OKVIS2-X Fisheye✗ ✗✓ ✓✗0.189 2320.7 4 ICL OpenVINS + DBoW Fisheye✗ ✗ ✗✓ ✓0.202 2308.8 5 Univ. of Lu...

    work page 2041

  16. [16]

    Benchmarking egocentric visual-inertial SLAM at city scale,

    A. Krishnanet al., “Benchmarking egocentric visual-inertial SLAM at city scale,” inIEEE/CVF Intl. Conference on Com- puter Vision, 2025

    work page 2025

  17. [17]

    A benchmark for the evaluation of RGB-D SLAM systems,

    J. Sturm, N. Engelhard, F. Endres, W. Burgard, and D. Cre- mers, “A benchmark for the evaluation of RGB-D SLAM systems,” inIEEE/RSJ Intl. Conf. on Intelligent Robots and Systems (IROS), 2012, pp. 573–580

    work page 2012

  18. [18]

    Hilti-Oxford dataset: A millimeter-accurate benchmark for simultaneous localization and mapping,

    L. Zhanget al., “Hilti-Oxford dataset: A millimeter-accurate benchmark for simultaneous localization and mapping,”IEEE Robotics and Automation Letters, vol. 8, no. 1, pp. 408–415, 2022

    work page 2022

  19. [19]

    Matterport3D: Learning from RGB-D data in indoor environments,

    A. Changet al., “Matterport3D: Learning from RGB-D data in indoor environments,” inIEEE Intl. Conf. on 3D Vision, 2017, pp. 667–676

    work page 2017

  20. [20]

    ScanNet: Richly-annotated 3D reconstructions of indoor scenes,

    A. Dai, A. X. Chang, M. Savva, M. Halber, T. Funkhouser, and M. Nießner, “ScanNet: Richly-annotated 3D reconstructions of indoor scenes,” inIEEE Int. Conf. Computer Vision and Pattern Recognition (CVPR), 2017, pp. 5828–5839

    work page 2017

  21. [21]

    A multi-view stereo benchmark with high- resolution images and multi-camera videos,

    T. Schopset al., “A multi-view stereo benchmark with high- resolution images and multi-camera videos,” inIEEE Int. Conf. Computer Vision and Pattern Recognition (CVPR), 2017, pp. 3260–3269

    work page 2017

  22. [22]

    Scan- Net++: A high-fidelity dataset of 3D indoor scenes,

    C. Yeshwanth, Y .-C. Liu, M. Nießner, and A. Dai, “Scan- Net++: A high-fidelity dataset of 3D indoor scenes,” inIntl. Conf. on Computer Vision (ICCV), 2023, pp. 12–22

    work page 2023

  23. [23]

    The Oxford Spires dataset: Benchmark- ing large-scale LiDAR-visual localisation, reconstruction and radiance field methods,

    Y . Tao, M. Á. Muñoz-Bañón, L. Zhang, J. Wang, L. F. T. Fu, and M. Fallon, “The Oxford Spires dataset: Benchmark- ing large-scale LiDAR-visual localisation, reconstruction and radiance field methods,”Intl. J. of Robotics Research, 2025

    work page 2025

  24. [24]

    Scene coordinate regression forests for camera relocalization in RGB-D images,

    J. Shotton, B. Glocker, C. Zach, S. Izadi, A. Criminisi, and A. Fitzgibbon, “Scene coordinate regression forests for camera relocalization in RGB-D images,” inIEEE Int. Conf. Computer Vision and Pattern Recognition (CVPR), 2013, pp. 2930–2937

    work page 2013

  25. [25]

    InLoc: Indoor visual localization with dense matching and view synthesis,

    H. Tairaet al., “InLoc: Indoor visual localization with dense matching and view synthesis,” inIEEE Int. Conf. Computer Vision and Pattern Recognition (CVPR), 2018, pp. 7199–7209

    work page 2018

  26. [26]

    Benchmarking 6DOF outdoor visual local- ization in changing conditions,

    T. Sattleret al., “Benchmarking 6DOF outdoor visual local- ization in changing conditions,” inIEEE Int. Conf. Computer Vision and Pattern Recognition (CVPR), 2018, pp. 8601–8610

    work page 2018

  27. [27]

    ConSLAM: Construction data set for SLAM,

    M. Trzeciaket al., “ConSLAM: Construction data set for SLAM,”J. of Computing in Civil Engineering, 2023

    work page 2023

  28. [28]

    The Hilti SLAM challenge dataset,

    M. Helmberger, K. Morin, B. Berner, N. Kumar, G. Cioffi, and D. Scaramuzza, “The Hilti SLAM challenge dataset,”IEEE Robotics and Automation Letters, vol. 7, no. 3, p. 7518–7525, 2022

    work page 2022

  29. [29]

    Hilti SLAM Challenge 2023: Benchmarking single + multi-session SLAM across sensor constellations in construction,

    A. D. Nair, J. Kindle, P. Levchev, and D. Scaramuzza, “Hilti SLAM Challenge 2023: Benchmarking single + multi-session SLAM across sensor constellations in construction,”IEEE Robotics and Automation Letters, vol. 9, no. 8, 2024

    work page 2023

  30. [30]

    Extending kalibr: Calibrating the extrinsics of multiple IMUs and of individual axes,

    J. Rehder, J. Nikolic, T. Schneider, T. Hinzmann, and R. Sieg- wart, “Extending kalibr: Calibrating the extrinsics of multiple IMUs and of individual axes,” inIEEE Intl. Conf. on Robotics and Automation (ICRA), 2016, pp. 4304–4311

    work page 2016

  31. [31]

    An enhanced unified camera model,

    B. Khomutenko, G. Garcia, and P. Martinet, “An enhanced unified camera model,”IEEE Robotics and Automation Let- ters, vol. 1, no. 1, pp. 137–144, 2015

    work page 2015

  32. [32]

    A generic camera model and calibration method for conventional, wide-angle, and fish-eye lenses,

    J. Kannala and S. Brandt, “A generic camera model and calibration method for conventional, wide-angle, and fish-eye lenses,”IEEE Trans. Pattern Anal. Machine Intell., vol. 28, no. 8, pp. 1335–1340, 2006

    work page 2006

  33. [33]

    MC2SLAM: Real-time inertial lidar odometry using two-scan motion com- pensation,

    F. Neuhaus, T. Koss, R. Kohnen, and D. Paulus, “MC2SLAM: Real-time inertial lidar odometry using two-scan motion com- pensation,” inPattern Recognition, vol. 11269, 2019

    work page 2019

  34. [34]

    Method for registration of 3- d shapes,

    P. J. Besl and N. D. McKay, “Method for registration of 3- d shapes,” inSensor fusion IV: control paradigms and data structures, vol. 1611. Spie, 1992, pp. 586–606

    work page 1992

  35. [35]

    evo: Python package for the evaluation of odom- etry and slam

    M. Grupp, “evo: Python package for the evaluation of odom- etry and slam.” https://github.com/MichaelGrupp/evo, 2017

    work page 2017

  36. [36]

    OKVIS2- X: Open keyframe-based visual-inertial SLAM configurable with dense depth or LiDAR, and GNSS,

    S. Boche, J. Jung, S. B. Laina, and S. Leutenegger, “OKVIS2- X: Open keyframe-based visual-inertial SLAM configurable with dense depth or LiDAR, and GNSS,”IEEE Trans. on Robotics, vol. 41, pp. 6064–6083, 2025

    work page 2025

  37. [37]

    Z-FLoc: Zero-Shot Floorplan Localization via Geometric Primitives

    A. Umemura, T. Kuwahara, M. Pollefeys, and D. Barath, “Z-floc: Zero-shot floorplan localization via geometric primi- tives,”CoRR, vol. abs/2606.04788, 2026

    work page internal anchor Pith review Pith/arXiv arXiv 2026

  38. [38]

    OpenVINS: A research platform for visual-inertial estima- tion,

    P. Geneva, K. Eckenhoff, W. Lee, Y . Yang, and G. Huang, “OpenVINS: A research platform for visual-inertial estima- tion,” inIEEE Intl. Conf. on Robotics and Automation (ICRA), Paris, France, 2020

    work page 2020

  39. [39]

    ORB-SLAM3: An accurate open-source library for visual, visual-inertial, and multimap SLAM,

    C. Campos, R. Elvira, J. J. G. Rodriguez, J. M. Montiel, and J. D. Tardos, “ORB-SLAM3: An accurate open-source library for visual, visual-inertial, and multimap SLAM,”IEEE Trans. Robotics, vol. 37, no. 6, pp. 1874–1890, 2021

    work page 2021

  40. [40]

    sqrt-vins: Robust and ultrafast square-root filter-based 3d motion tracking,

    Y . Peng, C. Chen, K. Wu, and G. Huang, “sqrt-vins: Robust and ultrafast square-root filter-based 3d motion tracking,” IEEE Trans. on Robotics (TRO), oct 2025

    work page 2025

  41. [41]

    Masked-attention Mask Transformer for Universal Image Segmentation

    B. Cheng, I. Misra, A. G. Schwing, A. Kirillov, and R. Gird- har, “Masked-attention mask transformer for universal image segmentation,”CoRR, vol. abs/2112.01527, 2021

    work page internal anchor Pith review Pith/arXiv arXiv 2021

  42. [42]

    Your ViT is Secretly an Image Segmenta- tion Model,

    T. Kerssieset al., “Your ViT is Secretly an Image Segmenta- tion Model,” inIEEE Int. Conf. Computer Vision and Pattern Recognition (CVPR), 2025

    work page 2025