3D Deep Learning OS — Course Syllabus

Name: 3D Deep Learning OS
Price: 1497 EUR

Reference syllabus for the 3D Deep Learning OS course delivered by the 3D Geodata Academy. It defines the learning objectives, audience, technical requirements, the module-by-module program, the assessment scheme, the results indicators and the legal terms of purchase.

"Master 3D deep learning end-to-end: from ANN/CNN fundamentals to PointNet++, KPConv, GrowSP and a deployable client-server AI app."

1. Course Overview

Dimension	Details
Format	Self-paced online course delivered through the 3D Geodata Academy LMS.
Price	€1 497 (excl. VAT). See section 7 for the legal payment terms.
Learning Objectives	Foundations of 3D deep learning: Understand ANN/CNN/Transformer/ResNet/EfficientNet and their adaptation to 3D data. (M1, M2) Train production-grade 3D models: Implement PointNet, PointNet++, KPConv and GrowSP from scratch on real datasets. (M3, M4) Ship a deployable 3D AI system: Architect, train, evaluate and deploy a client-server 3D AI application. (M5, M6)
Target Audience	ML engineers, R&D developers and data scientists building production 3D deep learning systems on point clouds, voxels and meshes.
Prerequisites	Working Python notions help. Watch the prerequisites primer →
Estimated Duration	Approximately 35 hours of focused work. Fully asynchronous.
Access	Direct enrolment via the 3D Geodata Academy. A 14-day legal cooling-off period applies.
Accessibility & Disability	All courses are open to learners with disabilities. A dedicated referent reviews each request to put the right pedagogical and technical adjustments in place. Referent: Dr. Florent Poux — howto@learngeodata.eu.
Contact	Dr. Florent Poux — howto@learngeodata.eu 3D Geodata Academy

A note from Dr. Florent PouxI built this OS to remove the gap between research papers and shipped 3D AI products. We do not stop at training a model on a benchmark — we ship a system that handles real LiDAR, scales, and that you can deploy.

2. Technical Stack & Pedagogical Means

Software stack: Python and the standard 3D ecosystem (Open3D, Laspy, NumPy, PyTorch, CloudCompare, Meshroom — adapted to the course focus).
Hardware: any modern laptop (Windows, macOS, Linux). GPU recommended for deep learning modules.
Datasets: reference datasets and notebooks provided.
Infrastructure: proprietary LMS with 24/7 access, automated quizzes, progress tracking and digital course materials.
Modality: alternates theory and hands-on practice — code, real datasets, software use and shippable project deliverables.
Theory resources: video lessons, written handouts, curated research articles and PhD-level references.

3. Course Structure

Module	Title & Focus
M1	Foundations Workflows, applications, 3D data types, ANN/CNN basics.
M2	Advanced architectures RNN/Transformers, ResNet, EfficientNet for 3D.
M3	3D data engineering for DL Point clouds, voxels, custom PyTorch classes.
M4	Reference architectures PointNet, PointNet++, KPConv on real data.
M5	Production systems Workflow, GrowSP, hybrid systems, generative models.
M6	Deployment Step-by-step 3D Python app, cloud production.

Why this structure, Dr. Florent PouxThe 6 modules are ordered the way I build systems in production, not the way a textbook would list them. If you are new to the topic, follow the sequence. If you are experienced, you can jump ahead, but come back to M6 before the oral defence. That's where everything ties together.

M1 — Foundations

Workflows, applications, 3D data types, ANN/CNN basics.

Overview of 3D deep learning and applications.
Introduction to 3D data types and DL workflows.
First deep learning Python setup.
Basics of ANN and coding one from scratch.
Basics of CNN and image classification.

M2 — Advanced architectures

RNN/Transformers, ResNet, EfficientNet for 3D.

Other DL architectures (RNN, Transformers).
Deep Residual Learning (ResNet).
Image recognition app with ResNet.
EfficientNet architecture and Python implementation.

M3 — 3D data engineering for DL

Point clouds, voxels, custom PyTorch classes.

Point clouds and voxels with Python.
Voxel custom dataset class (PyTorch).
3D DL system design thinking.
Code structure and mechanisms for 3D DL models.
Custom 3D point cloud class with PyTorch.

M4 — Reference architectures

PointNet, PointNet++, KPConv on real data.

PointNet fundamentals and architecture.
PointNet data preparation, model creation, training, inference.
KPConv: install, code, configuration, training, inference on real-world LiDAR.
PointNet++ on aerial LiDAR: functions, architecture, inference.

Mid-course checkpoint, Dr. Florent PouxWhen you reach M4 — Reference architectures, stop and apply what you've learned to a dataset you actually care about. The back half of the course goes faster when the first half sits on a real example, not a toy one.

M5 — Production systems

Workflow, GrowSP, hybrid systems, generative models.

Workflow and system design for production.
GrowSP for unsupervised + supervised semantic segmentation.
Generative models for 3D data.
Hybrid systems for 3D deep learning.
LLMs and AI for 3D content creation.

M6 — Deployment

Step-by-step 3D Python app, cloud production.

Production view, project structure, code structure.
Training and inference steps; YAML configuration.
Cloud production: setup, build, debug, finalisation.
Client-server AI app delivery.

Expert tip — Dr. Florent PouxSpend extra time on Module 3. Most teams who fail at 3D deep learning fail at data structure, not at architecture choice.

4. Assessment, Certificate & Grading

The OS program tier includes a project deliverable and an oral defence in addition to the quiz-based progression.

Stage	Activity	Validation
Before the course	Positioning quiz.	Informative.
During the course	End-of-module quizzes.	Score ≥ 70 % per quiz.
End of the course	Final quiz.	Score ≥ 80 %.
End of the course	Project deliverable submission.	Reviewed against published rubric.
End of the course	Oral defence with Dr. Florent Poux (45 min).	Score ≥ 15 / 25.

Conditions to obtain the certificate

Validate every end-of-module quiz (≥ 70 %).
Validate the final quiz (≥ 80 %).
Submit the project deliverable and pass the oral defence (≥ 15/25).

Grading scale

Certified — Pass: all criteria validated.
Certified with Merit: oral defence ≥ 18/25.
Certified with Distinction: oral defence ≥ 22/25 and quiz average ≥ 90 %.

Successful learners receive the OS certificate and the Alumni digital badge.

Accessibility & disability: all evaluations can be adapted (extended time, alternative formats, oral or written substitution) on request to the disability referent howto@learngeodata.eu.

5. Course Results & Quality Indicators

3D Geodata Academy publishes its course performance indicators transparently. Figures below cover this course and are updated at the end of each session.

Indicator	Current Result	Target
Number of enrolled learners	Data being consolidated	Continuous growth
Satisfaction rate	Data being consolidated	> 95 %
Success rate (certificate obtained)	Data being consolidated	> 85 %
Drop-out / interruption rate	Data being consolidated	< 5 %
Recommendation rate	Data being consolidated	> 90 %

Indicators consolidated from in-LMS quizzes and end-of-course satisfaction surveys. Last update: April 2026.

6. Next Step

This OS course gives you a complete operational system. To go further with structured mentorship and a wider curriculum, secure your spot below or join the 3D AI Accelerator.

🛒 Secure your spot 🚀 Join the 3D AI Accelerator

The 3D AI Accelerator adds direct mentorship with Dr. Florent Poux, full access to the complete course library (20+ courses), monthly analytics on the 3D spatial AI ecosystem, curated research papers and the private job board with reviews and notes on which roles are worth pursuing.

7. Legal, Accessibility & Purchase Conditions

Digital accessibility

3D Geodata Academy is committed to making its content accessible to learners with disabilities. A dedicated referent oversees content accessibility (captioning, transcripts, screen-reader friendly layouts, alternative evaluation formats). Contact: howto@learngeodata.eu.

Access for learners with disabilities

Every course can be adapted upon request. A short questionnaire at enrolment captures the pedagogical and technical adjustments needed. Disability referent: Dr. Florent Poux — howto@learngeodata.eu.

Payment terms — IP-protection caution & 14-day retraction

Because course content is delivered digitally and immediately accessible, the purchase is structured as follows to protect the intellectual property while preserving your legal right of retraction:

At checkout, the payment is collected as a caution / security deposit for IP infringement protection. Access to the LMS is granted immediately.
The deposit is held for 14 calendar days, matching the legal cooling-off period for distance contracts.
If you exercise your right of retraction within those 14 days and have not consumed a substantial part of the content, the deposit is refunded in full.
At the expiry of the 14-day period, in the absence of a retraction request, the deposit is automatically converted into the actual payment.

By purchasing, the learner acknowledges that the course materials are original works protected by copyright. Any reproduction, redistribution or commercial reuse without prior written consent is prohibited.

Data protection (GDPR)

Personal data is processed for the sole purpose of delivering the course, tracking progress, issuing the certificate and providing customer support. Access, rectification or deletion: howto@learngeodata.eu.

General terms of sale

Full general terms of sale are available on request and joined to every order confirmation.