Apply now
Master'sAutonomous, ADAS & Software-Defined Vehicle Applications open

Master’s in Photorealistic Sensor Simulation and Synthetic Data Engineering

Online master's programme of 1,900 hours in photorealistic sensor simulation and synthetic data engineering, structured in 12 modules covering photorealistic rendering, camera, LiDAR and radar modelling, neural rendering, synthetic training data, sensor model validation and governance (ASAM OSI, ASAM OpenSCENARIO, ASAM OpenDRIVE), with an assigned technical tutor.

Duration1900 h
ModeOnline
LanguageEnglish
Start datesSet by the faculty
AwardSEIUM Institute diploma
Enrol now View syllabus Ask an advisor
Virtual lab · try it before you enrol

Take the controls.

Run a real engineering trade-off from this field. Move the sliders, watch the model react in real time and beat the challenge.

SIM · LIVE ●
Learning outcomes

What you will be able to do

01

Analyse fidelity levels in sensor simulation.

02

Apply photorealistic rendering techniques.

03

Physically model cameras, LiDAR and radar.

04

Generate synthetic datasets for training.

05

Apply neural rendering to driving scenes.

06

Validate the credibility of sensor models.

07

Develop a photorealistic simulation and synthetic data project.

Profile

Who it's for

  • Sensor simulation engineers seeking deeper expertise in photorealistic models.
  • Synthetic data engineers building training datasets for perception.
  • 3D technical artists moving into automotive simulation.
  • Perception engineers who want to train and test with synthetic data.
  • Researchers in neural rendering applied to driving scenes.
  • Validation engineers using simulation in their test chains.
  • Engineering or science graduates seeking to enter the automotive sector.
Standards & tools

What you'll work with

  • ASAM OSI (open simulation interface for sensors)
  • ASAM OpenSCENARIO (scenario description format)
  • ASAM OpenDRIVE (road network description format)
  • ISO 21448 (SOTIF – safety of the intended functionality)
  • ISO 34502 (scenario-based safety evaluation)
  • Regulation (EU) 2024/1689 (AI Act) (EU artificial intelligence regulation)
  • Modelica Association FMI 3.0 (functional mock-up interface for co-simulation)
  • ISO 26262 (functional safety of road vehicles)
  • CARLA
  • Unreal Engine
  • NVIDIA Omniverse
  • Blender
  • PyTorch
Syllabus

12 modules · 1900 h

  1. 1.1The role of sensor simulation in ADAS
  2. 1.2Fidelity levels of sensor models
  3. 1.3The domain gap between simulation and reality
  4. 1.4Uses in training and in validation
  5. 1.5The simulation chain of a sensor
  6. 1.6Real-time versus offline requirements
  7. 1.7The ASAM OSI standard for sensors
  8. 1.8The simulation tools market
  9. 1.9Open credibility challenges
  10. 1.10Case study: comparison of sensor simulators
  1. 2.1Rasterisation versus ray tracing
  2. 2.2Path tracing and light sampling
  3. 2.3Physically based PBR materials
  4. 2.4Global illumination and reflections
  5. 2.5Weather and atmosphere simulation
  6. 2.6Unreal Engine and Unity engines
  7. 2.7NVIDIA Omniverse and RTX
  8. 2.8GPU performance and parallelisation
  9. 2.93D asset management
  10. 2.10Lab: night scene in Unreal Engine
  1. 3.1Optical lens model and distortion
  2. 3.2Spectral response of the sensor
  3. 3.3Read noise and shot noise
  4. 3.4Rolling shutter and motion blur
  5. 3.5HDR imaging and tone mapping
  6. 3.6LED source flicker
  7. 3.7Simulated ISP pipeline
  8. 3.8Validation with real cameras
  9. 3.9Image similarity metrics
  10. 3.10Practical: camera noise model
  1. 4.1Ray tracing for LiDAR
  2. 4.2Infrared reflectivity of materials
  3. 4.3LiDAR scanning patterns
  4. 4.4Effects of rain and fog on LiDAR
  5. 4.5Radar simulation by ray tracing
  6. 4.6Radar cross-section of objects
  7. 4.7Multipath and ghosts in radar
  8. 4.8Signal-level simulation
  9. 4.9Validation of radar models
  10. 4.10Workshop: simulated LiDAR with fog
  1. 5.1Vehicle and pedestrian asset libraries
  2. 5.2Procedural city generation
  3. 5.3Appearance and texture variation
  4. 5.4Pedestrian and cyclist animation
  5. 5.53D reconstruction of real environments
  6. 5.6Photogrammetry for digital twins
  7. 5.7Managing scene variety
  8. 5.8Rare scenarios and edge cases
  9. 5.93D content licensing
  10. 5.10Lab: procedural city in CARLA
  1. 6.1NeRF neural radiance fields
  2. 6.23D Gaussian splatting
  3. 6.3Reconstruction from fleet data
  4. 6.4Editing reconstructed scenes
  5. 6.5Inserting actors into real scenes
  6. 6.6Sensor simulation with neural models
  7. 6.7Diffusion models for driving images
  8. 6.8Quality versus speed
  9. 6.9Limitations of physical consistency
  10. 6.10Practical: reconstruction with Gaussian splatting
  1. 7.1Generation of synthetic datasets
  2. 7.2Perfect automatic labelling
  3. 7.3Domain randomisation
  4. 7.4Mixing real and synthetic data
  5. 7.5Sim-to-real domain adaptation
  6. 7.6Image translation with GANs
  7. 7.7Public synthetic datasets
  8. 7.8Evaluating the accuracy benefit
  9. 7.9Biases introduced by simulation
  10. 7.10Workshop: training with synthetic data
  1. 8.1Model validation methodologies
  2. 8.2Comparison at raw data level
  3. 8.3Comparison at detection level
  4. 8.4Distance metrics between distributions
  5. 8.5Tests with replica scenarios
  6. 8.6Model uncertainty
  7. 8.7Credibility according to simulation standards
  8. 8.8Validity documentation
  9. 8.9Iterative model improvement
  10. 8.10Lab: real-versus-simulated comparison with FID
  1. 9.1OSI and FMI interfaces
  2. 9.2Co-simulation of sensors and vehicle
  3. 9.3Injection into HIL hardware
  4. 9.4Real-time simulation
  5. 9.5Scaling in the cloud
  6. 9.6Campaign orchestration
  7. 9.7Model version management
  8. 9.8Reproducibility of results
  9. 9.9Computing costs
  10. 9.10Practical: parallel campaign in the cloud
  1. 10.1Traceability of synthetic data
  2. 10.2Documentation of generated datasets
  3. 10.3Privacy through synthetic data
  4. 10.4AI Act requirements on data
  5. 10.5Quality and representativeness
  6. 10.6Licences and intellectual property
  7. 10.7Life-cycle management
  8. 10.8Auditing synthetic data
  9. 10.9Industry best practices
  10. 10.10Case study: synthetic data policy
  1. 11.1CARLA and AirSim simulators
  2. 11.2Commercial simulation platforms
  3. 11.3NVIDIA DRIVE Sim
  4. 11.4Data generation tools
  5. 11.5USD scene formats
  6. 11.6Related ASAM standards
  7. 11.7The open-source community
  8. 11.8Tool selection
  9. 11.9Technology trends in simulation
  10. 11.10Workshop: generation pipeline with Omniverse
  1. 12.1Definition of the use case
  2. 12.2Selection of simulation tools
  3. 12.3Sensor modelling
  4. 12.4Scene generation
  5. 12.5Generation of the synthetic dataset
  6. 12.6Validation of the models
  7. 12.7Evaluation of the impact on perception
  8. 12.8Conclusions and future work
  9. 12.9Thesis report
  10. 12.10Master's Thesis: defence before a panel
Methodology, software & labs

How you'll learn

100% online training on the SEIUM campus, with downloadable material, recorded classes and an assigned technical tutor. There are no fixed timetables: you progress at your own pace within each intake, making it compatible with work.

Each module combines theory, guided reading of the original standard and applied exercises. The working software is CARLA, Unreal Engine, NVIDIA Omniverse, Blender and PyTorch, in free, academic or evaluation versions. Testing is studied through real procedures: generation of labelled synthetic datasets, validation of sensor models against real data and neural scene reconstruction. Assessment is continuous for each module, plus the final Master's Thesis.

Standards covered: ASAM OSI, ASAM OpenSCENARIO, ASAM OpenDRIVE, ISO 21448, ISO 34502, Regulation (EU) 2024/1689 (AI Act), Modelica Association FMI 3.0, ISO 26262.

Assigned technical tutor:every module ends with a deliverable that your tutor marks individually.
Standards-based learning:guided reading of ASAM OSI, ASAM OpenSCENARIO and ASAM OpenDRIVE applied to real cases, not as a theoretical annex.
Industry software:CARLA, Unreal Engine, NVIDIA Omniverse, Blender and PyTorch, in free, academic or evaluation versions.
Master's Thesis with defence:a complete photorealistic simulation project, from sensor modelling and scene generation to a validated synthetic dataset and its impact on perception, defended before a panel.
Flexible format:100% online, no fixed timetables, compatible with full-time work.
Capstone project

Build it end to end

Your final project follows the real engineering workflow, step by step, reviewed by your tutor.

Photorealistic scene set-up
Build a night driving scene in Unreal Engine with physically based materials and lighting.
Physical sensor models
Model camera noise and simulate LiDAR under fog conditions.
Synthetic dataset generation
Generate a labelled synthetic dataset from a procedural city in CARLA and train a perception model with it.
Sensor model validation
Compare real and simulated data using FID and distribution metrics.
Master's Thesis
A complete photorealistic simulation project, from sensor modelling and scene generation to a validated synthetic dataset and its impact on perception, defended before a panel.
Career opportunities

Where this takes you

Sensor simulation engineerSynthetic data engineer3D technical artistPerception engineerNeural rendering researcherValidation engineer
Admissions & scholarships

Requirements

  • A university degree in engineering, science or architecture, or equivalent demonstrable professional experience.
  • An internet connection and a computer capable of running the programme software.
  • English sufficient to read technical standards.

Ready to start?

Send your application today. Our admissions team replies within 72 hours with your study plan and funding options.

Apply now Scholarships
FAQ

Frequently asked questions

The programme totals 1,900 hours over 12–14 months. You set your own pace within each intake, and your tutor helps you plan the workload around your job.

You work with CARLA, Unreal Engine, NVIDIA Omniverse, Blender and PyTorch, using free, academic or evaluation versions. Your tutor indicates the free alternative wherever one exists.

A SEIUM Institute diploma, awarded on passing the continuous assessment and the Master's Thesis. It is SEIUM's own qualification, not an official state degree; its recognition depends on the programme completed and the regulations of each country.

Yes. Modules passed in a course or postgraduate diploma in the same area are recognised in the higher programme. Ask about the recognition policy when you enrol.

A degree in engineering, science or architecture (or equivalent professional experience), a computer able to run the software and English sufficient to read technical standards.

Start dates are set by SEIUM's faculty for each intake. Our admissions team will confirm the next available date when you apply.

Keep exploring

Related programmes

See all in Autonomous, ADAS & Software-Defined Vehicle
Master's6,610 $

Master’s in Semantic Mapping and Risk-Prioritised Maps Engineering

Online master's programme of 1,900 hours in semantic cartography and risk-prioritised maps engineering, structured in 12 modules covering semantic map models and ontologies, semantic segmentation, road…

1900 hOnlineAutonomous, ADAS & Software-Defined Vehicle
Master's9,970 $

Master’s in Perception & Sensors Engineering

Online master's programme of 1,900 hours in perception and sensors engineering. 12 modules covering perception for automated vehicles, cameras and computer vision, automotive radar, LiDAR, ultrasonic…

1900 hOnlineAutonomous, ADAS & Software-Defined Vehicle
Master's11,090 $

Master’s in Autonomous Urban Buses and Shuttles Engineering

Online master's programme of 1,900 hours in urban autonomous bus and shuttle engineering: 12 modules covering vehicle platforms, urban perception and localisation, bus planning and control,…

1900 hOnlineAutonomous, ADAS & Software-Defined Vehicle
Master’s in Photorealistic Sensor Simulation and Synthetic Data EngineeringEnrol
Related programmes

More in Autonomous, ADAS & Software-Defined Vehicle

Master’s in Functional Safety, Cyber and Compliance EngineeringView programme →Master’s in Software-Defined Vehicle DevOps EngineeringView programme →Master’s in Human-Vehicle Interaction Engineering at Levels 2–4View programme →Master’s in Dev Platforms Engineering for SDVs — Vehicle-Centric APIs, App Stores, Sandboxing and PermissionsView programme →Master’s in MapOps Engineering: HD Map Production and MaintenanceView programme →Master’s in Robust Perception in Adverse Conditions EngineeringView programme →

All Autonomous, ADAS & Software-Defined Vehicle programmes → · How to apply · Fees & financing · Scholarships

Scroll to Top
SEIUM – Institute of Advanced Engineering
Powered by  GDPR Cookie Compliance
Privacy Overview

This website uses cookies so that we can provide you with the best user experience possible. Cookie information is stored in your browser and performs functions such as recognising you when you return to our website and helping our team to understand which sections of the website you find most interesting and useful.