arxiv: 2604.19194 · v1 · submitted 2026-04-21 · 💻 cs.GR

Recognition: unknown

sumo3Dviz: A three dimensional traffic visualisation

Kevin Riehl , Julius Schlapbach , Anastasios Kouvelas , Michail A. Makridis

Authors on Pith no claims yet

Pith reviewed 2026-05-10 01:37 UTC · model grok-4.3

classification 💻 cs.GR

keywords 3D visualizationtraffic simulationSUMOPython pipelineopen sourcevehicle trajectoriesfirst-person perspectivemobility research

0 comments

The pith

sumo3Dviz converts standard SUMO outputs into high-quality 3D videos with external and first-person views.

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

The paper presents sumo3Dviz as a lightweight open-source Python pipeline that turns vehicle trajectories and signal states from SUMO traffic simulations into 3D renderings. This fills a gap for applications needing intuitive visuals, such as mobility psychology, acceptance research, and stated-preference experiments, where 2D or numerical results are too abstract. The tool runs independently of game engines, installs via pip, and supports batch video creation across operating systems. It specifically solves the problem of generating smooth motion by interpolating discrete simulation steps and smoothing vehicle orientations.

Core claim

The central claim is that sumo3Dviz provides a simple, scriptable Python framework to convert standard SUMO simulation outputs into realistic 3D renderings, supporting both cinematic external cameras and first-person driver perspectives while remaining reproducible and free of proprietary dependencies.

What carries the argument

The central mechanism is the trajectory interpolation and orientation smoothing step that turns discrete SUMO outputs into visually coherent vehicle motion within the Python-based 3D rendering pipeline.

If this is right

Batch video generation becomes feasible for large-scale scenario analysis and automated experiment pipelines.
First-person perspectives enable driver-level experiences for virtual stated-preference studies without additional software licenses.
Educational demonstrations and communication of simulation results gain realistic visual support across platforms.
Reproducible workflows for mobility research become accessible to users without game-engine expertise.

Where Pith is reading between the lines

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

The same interpolation approach could be tested on outputs from other microsimulation tools to check if visual coherence generalizes.
Generated videos might serve as training data for computer-vision models that analyze traffic scenes from driver viewpoints.
Integration with head-mounted displays could turn the first-person mode into a low-cost virtual-reality testing environment.

Load-bearing premise

That the smoothed 3D motion from discrete simulation steps will look natural enough to support valid human perception studies in traffic psychology and acceptance research.

What would settle it

A controlled user study in which participants give inconsistent preference ratings or acceptance scores for the same traffic scenarios when viewed in the generated 3D videos versus real-world footage or higher-fidelity renderings.

Figures

Figures reproduced from arXiv: 2604.19194 by Anastasios Kouvelas, Julius Schlapbach, Kevin Riehl, Michail A. Makridis.

**Figure 1.** Figure 1: Overview of the sumo3Dviz workflow, from SUMO inputs to rendered video output. Simulation Log Files sumo3Dviz 3D Visualization User Configuration Vehicle Positions Signal States YAML XML XML Simulation Files XML Network XML POIs V I Z Video Files (.mp4) Image Files (.png) 3.1 Input Data and Preprocessing The input to sumo3Dviz consists of SUMO network and configuration files, as well as the simulation outp… view at source ↗

**Figure 2.** Figure 2: Available textures for ground and sky rendering in [PITH_FULL_IMAGE:figures/full_fig_p006_2.png] view at source ↗

**Figure 3.** Figure 3: Road network rendering approach: layered structure (left) and geometric construction [PITH_FULL_IMAGE:figures/full_fig_p006_3.png] view at source ↗

**Figure 5.** Figure 5: 6 [PITH_FULL_IMAGE:figures/full_fig_p006_5.png] view at source ↗

**Figure 4.** Figure 4: Static objects in sumo3Dviz (trees and buildings). Define Positions in Net-Edit Tool (Additional-Mode) Generated XML Files Points for Objects Lines for Fences Final Result [PITH_FULL_IMAGE:figures/full_fig_p007_4.png] view at source ↗

**Figure 5.** Figure 5: Positioning static objects for sumo3Dviz in netedit. Traffic lights can be placed in the 3D visualisation as well. Given the log files from the SUMO simulation, they can display the signal states at given times. sumo3Dviz offers three traffic light designs, as shown in [PITH_FULL_IMAGE:figures/full_fig_p007_5.png] view at source ↗

**Figure 6.** Figure 6: Traffic light designs in sumo3Dviz. In terms of moving objects (vehicles) a selection of ten car models are available, as shown in 7 [PITH_FULL_IMAGE:figures/full_fig_p007_6.png] view at source ↗

**Figure 7.** Figure 7: Each vehicle reported in SUMO’s trajectory log file is randomly assigned one of the car [PITH_FULL_IMAGE:figures/full_fig_p008_7.png] view at source ↗

**Figure 8.** Figure 8: Network geometry of the Ronda de Dalt highway network used in the case study, showing on-ramps, off-ramps, and residential areas. Network Selected Vehicle Trajectory Cinematic Camera Flight Trajectory Fixed Camera 1km 200m 200m 60m 5.2 Simulation Scenario The case study is based on a demand-calibrated SUMO simulation of the Ronda de Dalt ring road [22]. The simulated network spans approximately 6.5 km and … view at source ↗

**Figure 9.** Figure 9: Visualisation modes of sumo3Dviz. Mode 2: Lagrangian (moving, ego perspective) Mode 1: Eulerian (fixed camera perspective) Mode 3: Cinematic (moving, fly-through perspective) Mode 4: Interactive (user controllable perspective) 5.5 Visual Customisation The visualisations in this case study are rendered as video sequences. Key rendering parameters include the simulated time interval, frame rate, image resolu… view at source ↗

read the original abstract

Traffic microsimulation software such as SUMO generate rich spatio-temporal data describing individual vehicle movements, interactions, and support the development of control strategies. While numerical outputs and 2D visualisations are sufficient for many technical analyses, they are often inadequate for applications that require intuitive interpretation, effective communication, or human-centred evaluation. In particular, user studies in mobility psychology, acceptance research, and virtual experience stated-preference experiments require realistic visualisations that reflect how traffic scenarios are perceived from a human perspective. This paper introduces sumo3Dviz, a lightweight, open-source 3D visualisation pipeline for SUMO traffic simulations. It converts standard SUMO simulation outputs, such as vehicle trajectories and signal states, into high-quality 3D renderings using a Python-based framework. In contrast to heavyweight game-engine-based approaches or tightly coupled co-simulation frameworks, sumo3Dviz is designed to be simple, scriptable, and reproducible. The tool is installable through the pip package manager, runs across operating systems, and works independently of any proprietary software or licenses. sumo3Dviz supports both external camera views and first-person perspectives, enabling cinematic overviews as well as driver-level experiences. The rendering process is optimized for batch video generation, making it suitable for large-scale scenario visualisation, educational demonstrations, and automated experiment pipelines. A key technical challenge addressed by the tool is trajectory interpolation and orientation smoothing, enabling visually coherent motion from discrete simulation outputs. Source Code on project's GitHub page: https://github.com/DerKevinRiehl/sumo3dviz/.

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.

Desk Editor's Note private letter to a colleague

sumo3Dviz is a practical lightweight Python tool for 3D SUMO visualization with first-person support, but the paper is mostly a feature description without benchmarks or usage evidence.

read the letter

The main thing to know is that this paper introduces sumo3Dviz, a pip-installable Python package that takes standard SUMO trajectory and signal outputs and produces 3D rendered videos, including external views and first-person driver perspectives, plus batch processing for multiple scenarios. It positions itself as a simpler alternative to game-engine setups for researchers who need intuitive visuals beyond 2D plots or raw numbers. The interpolation and orientation smoothing steps to create coherent motion from discrete simulation steps are a sensible technical choice, and the emphasis on cross-platform use, no proprietary dependencies, and scriptability makes it easy to integrate into existing workflows. The GitHub link lets anyone check the implementation directly, which is the right way to handle a software contribution like this. What the paper does well is identify a clear gap for human-centered traffic studies in psychology, acceptance research, and stated-preference experiments, where realistic 3D views matter more than technical metrics alone. It keeps the scope narrow and focused on reproducibility rather than claiming broad advances. The softer spots are that the manuscript stays at the level of describing features and the problem it solves, without any quantitative results on rendering quality, speed comparisons, visual fidelity tests, or even sample outputs from real SUMO runs. The suitability for virtual experiments is asserted but not demonstrated, so readers have to install and try the code to judge whether the motion looks natural enough. This is not a fatal issue for a tool paper, but it does limit how much the text itself can be evaluated. This work is for people already using SUMO who want a quick way to generate 3D videos for communication or experiments, not for graphics researchers or those seeking new algorithms. A reader in traffic microsimulation or mobility human factors would get direct value from the code and the setup instructions. It deserves a serious referee because the contribution is concrete, the code is public, and the problem it targets is real for a slice of the community. I would recommend sending it to peer review rather than a desk reject, with the expectation that reviewers will likely ask for more validation examples or usage notes.

Referee Report

0 major / 2 minor

Summary. The paper introduces sumo3Dviz, a lightweight, open-source Python-based 3D visualisation pipeline for SUMO traffic simulations. It converts standard SUMO simulation outputs into high-quality 3D renderings, supporting external camera views and first-person perspectives. The tool addresses trajectory interpolation and orientation smoothing to enable visually coherent motion from discrete data.

Significance. If the described functionality holds, sumo3Dviz offers a practical, accessible tool for researchers needing 3D traffic visualizations for human-centered studies. The open-source, pip-installable design and independence from proprietary software are strengths that promote reproducibility and broad adoption.

minor comments (2)

The paper would be strengthened by the inclusion of example images or video frames demonstrating the 3D rendering output.
Providing more details on the specific methods for trajectory interpolation and orientation smoothing in the main text, rather than relying solely on the linked repository, would improve accessibility.

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for the positive summary of sumo3Dviz and for recognizing its practical value for human-centered traffic studies. We appreciate the recommendation for minor revision. No specific major comments were provided in the report, so we have no points requiring detailed rebuttal or manuscript changes at this stage.

Circularity Check

0 steps flagged

No significant circularity; tool-description paper is self-contained

full rationale

The manuscript introduces sumo3Dviz as a pip-installable Python pipeline that ingests standard SUMO trajectory and signal outputs and produces 3D renderings with external and first-person views. No equations, fitted parameters, predictions, or derivation chains appear in the provided text. The technical challenge of trajectory interpolation and orientation smoothing is presented as an implementation detail rather than a claim that reduces to its own inputs. The work is directly testable via the linked GitHub repository and contains no self-citation load-bearing arguments or uniqueness theorems. This is the expected outcome for a software artifact paper with no mathematical content.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

This is a software tool introduction paper with no mathematical derivations, free parameters, axioms, or invented entities; the contribution is the pipeline implementation itself.

pith-pipeline@v0.9.0 · 5596 in / 1116 out tokens · 50456 ms · 2026-05-10T01:37:10.228898+00:00 · methodology

discussion (0)

Reference graph

Works this paper leans on

25 extracted references · 18 canonical work pages

[1]

Accessed: 2025-02-24

Ajuntament de Barcelona.Itineraris - Open Data Barcelona. Accessed: 2025-02-24. 2024. url:https://opendata-ajuntament.barcelona.cat/data/ca/dataset/itineraris

2025
[2]

Integrating SUMO in an urban digital twin-a case study from Munich

Sasan Amini et al. “Integrating SUMO in an urban digital twin-a case study from Munich”. In:SUMO User Conference 2023. 2023.doi:10.13140/rg.2.2.30752.15364

work page doi:10.13140/rg.2.2.30752.15364 2023
[3]

Digital twins

Michael Batty. “Digital twins”. In:Environment and Planning B: Urban Analytics and City Science45.5 (2018), pp. 817–820.doi:10.1177/2399808318796416

work page doi:10.1177/2399808318796416 2018
[4]

Traffic simulation with aimsun

Jordi Casas et al. “Traffic simulation with aimsun”. In:Fundamentals of traffic simulation. Springer, 2010, pp. 173–232.doi:10.1007/978-1-4419-6142-6_5

work page doi:10.1007/978-1-4419-6142-6_5 2010
[5]

El espacio p´ ublico y la infraestructura viaria en La Ronda de Dalt

Sandra D´ ıaz. “El espacio p´ ublico y la infraestructura viaria en La Ronda de Dalt”. MA thesis. Universitat de Barcelona, 2015.url:https://hdl.handle.net/2445/66383

2015
[6]

CARLA: An open urban driving simulator

Alexey Dosovitskiy et al. “CARLA: An open urban driving simulator”. In:Conference on Robot Learning (CoRL). PMLR. 2017, pp. 1–16.url:https://proceedings.mlr.press/ v78/dosovitskiy17a.html

2017
[7]

Visualizing transport fu- tures: The potential of integrating procedural 3D modelling and traffic micro-simulation in virtual reality applications

Alexander Erath, Noopur Maheshwari, and Kay W. Axhausen. “Visualizing transport fu- tures: The potential of integrating procedural 3D modelling and traffic micro-simulation in virtual reality applications”. In:Proceedings of the 16th Swiss Transport Research Conference (STRC). Ascona, Switzerland, 2017.doi:10.3929/ethz-b-000118798

work page doi:10.3929/ethz-b-000118798 2017
[8]

SUMO’s lane-changing model

Jakob Erdmann. “SUMO’s lane-changing model”. In:Modeling Mobility with Open Data: 2nd SUMO Conference 2014 Berlin, Germany, May 15-16, 2014. Springer. 2015, pp. 105–123. doi:10.1007/978-3-319-15024-6_7

work page doi:10.1007/978-3-319-15024-6_7 2014
[9]

Virtual reality in stated preference survey for walkability as- sessment

Giovana Facchini et al. “Virtual reality in stated preference survey for walkability as- sessment”. In:Transportation Research Part D: Transport and Environment139 (2025), p. 104545.doi:10.1016/j.trd.2024.104545

work page doi:10.1016/j.trd.2024.104545 2025
[10]

Microscopic traffic flow simulator VISSIM

Martin Fellendorf and Peter Vortisch. “Microscopic traffic flow simulator VISSIM”. In:Fun- damentals of traffic simulation. Springer, 2010, pp. 63–93.doi:10.1007/978-1-4419-6142- 6_2

work page doi:10.1007/978-1-4419-6142- 2010
[11]

The principles of calibrating traffic microsimulation models

Yaron Hollander and Ronghui Liu. “The principles of calibrating traffic microsimulation models”. In:Transportation35.3 (2008), pp. 347–362.doi:10.1007/s11116-007-9156-2

work page doi:10.1007/s11116-007-9156-2 2008
[12]

Visualization in transportation: Current practice and future directions

Ronald Hughes. “Visualization in transportation: Current practice and future directions”. In:Transportation Research Record1899.1 (2004), pp. 167–174.doi:10.3141/1899-21

work page doi:10.3141/1899-21 2004
[13]

Real-time visualization of city public transport provider data and prediction of future trends

Kristijan Juri´ c. “Real-time visualization of city public transport provider data and prediction of future trends”. MA thesis. University of Zagreb. Faculty of Transport and Traffic Sciences, 2024.url:https://urn.nsk.hr/urn:nbn:hr:119:643618

2024
[14]

Visualization of Future Transport Concepts

Mattias J Klein and Henrik Lund. “Visualization of Future Transport Concepts”. MA thesis. Chalmers University of Technology, 2009.url:https://odr.chalmers.se/server/api/ core/bitstreams/43857f85-97e4-47e4-ac94-ddbd4c276c3b/content

2009
[15]

Recent development and applications of SUMO—Simulation of Urban MObility

Daniel Krajzewicz et al. “Recent development and applications of SUMO—Simulation of Urban MObility”. In:International Journal On Advances in Systems and Measurements5.3– 4 (2012), pp. 128–138.url:https://personales.upv.es/thinkmind/SysMea/SysMea_v5_ n34_2012/sysmea_v5_n34_2012_4.html

2012
[16]

50th anniversary invited article—Autonomous vehicles and connected vehicle systems: Flow and operations considerations

Hani S Mahmassani. “50th anniversary invited article—Autonomous vehicles and connected vehicle systems: Flow and operations considerations”. In:Transportation Science50.4 (2016), pp. 1140–1162.doi:10.1287/trsc.2016.0712

work page doi:10.1287/trsc.2016.0712 2016
[17]

Micro-simulation modelling for traffic safety: A review and po- tential application to heterogeneous traffic environment

SM Sohel Mahmud et al. “Micro-simulation modelling for traffic safety: A review and po- tential application to heterogeneous traffic environment”. In:IATSS Research43.1 (2019), pp. 27–36.doi:10.1016/j.iatssr.2018.07.002

work page doi:10.1016/j.iatssr.2018.07.002 2019
[18]

An Open-Source Virtual Reality Traffic Co-Simulation for En- hanced Traffic Safety Assessment

Ahmad Mohammadi et al. “An Open-Source Virtual Reality Traffic Co-Simulation for En- hanced Traffic Safety Assessment”. In:Applied Sciences15.17 (2025), p. 9351.doi:10.3390/ app15179351. 13

2025
[19]

A Study of Reinforcement Learning Techniques for Path Tracking in Autonomous Vehicles

Ahmad Mohammadi et al. “Sumo2unity: An open-source traffic co-simulation tool to improve road safety”. In:2024 IEEE Intelligent Vehicles Symposium (IV). IEEE. 2024, pp. 2523–2528. doi:10.1109/IV55156.2024.10588571

work page doi:10.1109/iv55156.2024.10588571 2024
[20]

A modular architecture for procedural generation of towns, inter- sections and scenarios for testing autonomous vehicles

Ishaan Paranjape et al. “A modular architecture for procedural generation of towns, inter- sections and scenarios for testing autonomous vehicles”. In:2020 IEEE Intelligent Vehicles Symposium (IV). IEEE. 2020, pp. 162–168.doi:10.1109/IV47402.2020.9304625

work page doi:10.1109/iv47402.2020.9304625 2020
[21]

URLhttps://www

Mathias Pechinger and Johannes Lindner. “Sumonity: Bridging sumo and unity for enhanced traffic simulation experiences”. In:SUMO Conference Proceedings. Vol. 5. 2024, pp. 163–177. doi:10.52825/scp.v5i.1115

work page doi:10.52825/scp.v5i.1115 2024
[22]

In: 2025 IEEE 64th Conference on Decision and Control (CDC)

Kevin Riehl et al. “EQ-ALINEA–Equitable Ramp Metering For Sustainable Metropolitan Highways”. In:2025 IEEE 64th Conference on Decision and Control (CDC). IEEE. 2025, pp. 4970–4975.doi:10.1109/CDC57313.2025.11312855

work page doi:10.1109/cdc57313.2025.11312855 2025
[23]

Matthew Weinberg

Usama Shahdah, Frank Saccomanno, and Bhagwant Persaud. “Application of traffic mi- crosimulation for evaluating safety performance of urban signalized intersections”. In:Trans- portation Research Part C: Emerging Technologies60 (2015), pp. 96–104.doi:10.1016/j. trc.2015.06.010

work page doi:10.1016/j 2015
[24]

The State of the Art in Visual Analytics for 3D Urban Data

Benedikt Weber et al. “The State of the Art in Visual Analytics for 3D Urban Data”. In: Computer Graphics Forum. Vol. 43. 3. 2024.doi:10.1111/cgf.15112

work page doi:10.1111/cgf.15112 2024
[25]

Joining SUMO and Unreal Engine to Create a Bespoke 360 Degree Narrow Passage Driving Simulator

Peter Youssef, Katherine Plant, and Ben Waterson. “Joining SUMO and Unreal Engine to Create a Bespoke 360 Degree Narrow Passage Driving Simulator”. In:SUMO Conference Proceedings. Vol. 5. 2024, pp. 93–112.doi:10.52825/scp.v5i.1104. 14

work page doi:10.52825/scp.v5i.1104 2024