3D Geodata Academy

Designing PointNet Models for ML Engineers

EVERY 3D ARCHITECTURE SINCE 2017 STANDS ON POINTNET.

Design PointNet Models, from First Principles to Deployment

Implement the architecture that started 3D deep learning, in PyTorch, layer by layer. 8 lessons for ML engineers who want to own the model, not import it.

8
Engineering lessons
8+
Hours of content
100%
From-scratch build

Methods validated inside

AIRBUS CNES THALES META BMW ESRI

See the architecture take shape

From an empty Python file to a trained PointNet classifying real 3D objects.

2017

The year PointNet changed 3D ML. Every point-based architecture since builds on its core ideas.

0

Students trained worldwide across 80 countries.

12+ yrs

Production experience distilled into structured, repeatable workflows.

You can import PointNet. Can you defend it?

Any ML engineer can pip install a 3D library and call a pretrained model. Then the interview question lands: “Why is max pooling the symmetric function here? What does the T-Net actually align? Why does your accuracy collapse on rotated scans?” Imports do not answer questions. Understanding does.

PointNet is the ideal architecture to truly own: small enough to implement in a few hundred lines, deep enough to contain the core ideas of all point-based learning, permutation invariance, shared MLPs, and learned alignment. Build it once properly, and every 3D paper you read afterward makes sense.

Why build from scratch in 2026

Architectures change every year. The reasoning behind them does not. When you have implemented the T-Net, debugged the pooling, and watched the loss curves yourself, you can evaluate any new 3D architecture in an afternoon. That judgment is what separates an ML engineer from a model consumer.

What you’ll build

A complete PointNet system, written by you, trained on real data.

🧠

PointNet, layer by layer

The full architecture in PyTorch: input and feature T-Nets, shared MLPs, and the max pooling that makes it order-invariant.

📦

Data preparation pipeline

The unglamorous 80% done right. Point sampling, normalization, augmentation, and PyTorch datasets and loaders built for 3D.

📈

Training + evaluation loop

Loss design, training dynamics, and the evaluation metrics that tell you whether the model generalizes or memorizes.

⚙️

Clean engineering setup

A reproducible deep learning environment and a project structure you can reuse for every 3D model you build after this one.

🔍

Inference on real scans

Run your trained model on unseen 3D data, inspect the failure cases, and learn what they reveal about the architecture.

🧭

Architecture intuition

The mental model to read PointNet++, point transformers, and whatever comes next. The ideas transfer, the imports do not.

Note from Dr. Poux

PointNet changed how we process 3D data in machine learning. If you are an ML engineer who wants to truly understand the architecture, not just import it, this is the course I wish I had when I started. We build everything, we break a few things on purpose, and you leave owning the model.

How this course works

Engineer-to-engineer, code-first, no hand-waving.

100% asynchronous

Access everything 24/7 on the LMS. Self-paced. No live sessions required.

💻

From-scratch implementation

Every layer written and explained, not imported. You see why each design decision exists before you code it.

📊

Real 3D datasets

Train and evaluate on real point cloud data, with the class imbalance and noise that benchmarks hide from you.

🚀

ML engineering patterns

Reproducible configs, clean dataset classes, and checkpointing habits that transfer to every model you ship.

🔄

Lifetime access

One payment, permanent access. Every future update included.

🧩

Gateway to 3D DL

PointNet is the foundation lesson of point-based deep learning. Everything in the 3D Deep Learning OS builds on what you learn here.

Built for ML engineers specifically

This is not a survey course. It assumes you can write Python, want to see tensors and shapes, and care about why the architecture works. If you want the broader segmentation method map instead, the Applied Semantic Segmentation course is the wider entry point.

The Curriculum

8 lessons. From an empty repo to a trained, evaluated PointNet.

Prerequisites

This course is for ML engineers and researchers who want to own point-based deep learning at the implementation level.

  • Python (intermediate): comfortable with classes, NumPy, and reading library code
  • ML basics: you know what a loss function and a training loop are. Prior PyTorch helps but is built up in the course
  • Hardware: a GPU shortens training, but datasets are sized so a CPU still works. 16 GB RAM recommended
  • Software: Python, PyTorch, NumPy, Open3D. All free and open-source

No prior 3D deep learning experience required. The architecture is built from first principles.

01Engineering setup
Environment + Project Structure

Start like you intend to ship. The starting folder, a reproducible deep learning environment, and the project structure the whole build lives in.

3D deep learning starting folder
A first deep learning Python setup
Reproducibility habits that stick
02PointNet architecture
Deep Dive + Implementation

The heart of the course. T-Nets, shared MLPs, symmetric pooling, every component explained, then implemented in PyTorch.

PointNet architecture: deep dive
Permutation invariance and why it matters
Full PyTorch implementation, layer by layer
03Data preparation
The Real 80%

Two full lessons on the stage that decides your accuracy. Sampling, normalization, augmentation, and PyTorch data pipelines for point clouds.

Data preparation part 1, sampling and normalization
Data preparation part 2, datasets and loaders
Augmentation strategies for 3D
04Training and evaluation
Train, Infer, Evaluate

Close the loop. Model creation, training dynamics, inference on unseen scans, and the evaluation that tells you the truth about generalization.

Model creation and training
Inference and evaluation on real data
Reading failure cases like an engineer
Dr. Florent Poux, founder of the 3D Geodata Academy

Your instructor

Dr. Florent Poux

I’ve spent 12+ years in 3D geospatial: from field surveys with total stations to building AI systems for Fortune 500 companies. I published the O’Reilly book on 3D Data Science with Python. I’ve advised startups valued at over 15M EUR. I’ve held a professorship, taught at university, and led R&D for some of the largest organizations in the space.

I don’t teach syntax. I teach judgment. Every module is built around real decisions I’ve faced in production. Which neural renderer fits an industrial inspection job. How to architect a semantic pipeline that doesn’t choke on 500M points. When to use algorithmic methods and when to switch to deep learning.

15,000+ readers
O’Reilly author
PhD in 3D geospatial
12+ years in the field
ISPRS Award winner
1,500+ citations
Start Building with Me

What students say

Engineers, GIS professionals, and researchers from 80 countries.

Get lifetime access

One payment. The full architecture, the code, and every update.

Designing PointNet Models

Complete implementation curriculum + PyTorch source code + datasets + lifetime updates

€297 one-time
  • 8 lessons (8+ hours, 4 modules)i
  • Complete PyTorch source code + datasets
  • From-scratch architecture implementation
  • Training, inference, and evaluation pipelines
  • Lifetime access + all future updatesi
  • 90-day results guaranteei
Start Building Now

Zero-risk guarantee: If you don’t see real results within 90 days, I’ll refund you in full. No questions.

SECURE CHECKOUT

The complete ecosystem

3D AI Architect Program

The complete spatial AI curriculum, delivered in 3 tiers. Pick the depth that matches where you are — Foundations to get moving, Professional for the full OS stack, Ultimate for live access and priority support.

  • 3D AI Acceleratori: 17 episodes in 6 acts
  • 3D Course Libraryi: 24+ standalone courses
  • All 4 OS courses (Professional & Ultimate tiers)
  • Neurones 3D software access
  • Monthly drop-in sessions with Dr. Poux (Ultimate)
  • Spatial AI job and market intel
  • Priority support + services access (Ultimate)
  • 300+ hours of content
Explore the Architect Program

What you’re getting access to

Everything I’ve built over 12+ years, from land surveying in the field to advising 15M EUR startups, compressed into one curriculum you can start today. Delivered by the first QUALIOPI-certified 3D geospatial academy.

2013
Engineer diploma in land surveying
ENGINEER
2015
Field surveyor + PhD research
2 YRS IN THE FIELD
2019
PhD in 3D geospatial AI
PhD DEFENDED
2020
ISPRS Dangermond Award + Professorship
1,500+ CITATIONS
2021
Fortune 500 R&D + startup advisor (15M+ EUR)
AIRBUS, CNES, BMW
2024
Splatting, Agents, Scene Graph R&D
FRONTIER
2025
O’Reilly book + 15K readers
60+ TUTORIALS
Today
15,000 students, 80 countries
QUALIOPI CERTIFIED
Enterprise-grade

Every pipeline was battle-tested on Fortune 500 projects processing billions of points. You’re getting the real playbook, not theory.

Research-backed

Methods validated by peer-reviewed publications, the ISPRS scientific community, and 1,500+ academic citations. Not guesswork.

Production-proven

Built by someone who surveyed in the field, defended a PhD, advised funded startups, and shipped products to Fortune 500 clients.

My commitment

I share more free content than most people put behind a paywall. That’s intentional. I want you to know exactly what you’re getting before you invest. This course is the concentrated, structured version of everything I know. No fluff. No filler. Just the production path.

Find the right path for you

From single courses to the complete ecosystem.

Feature Standalone Course Designing PointNet Models Course Library 3D AI Architecti Enterprise
Courses included 1 topic 4 modules Full catalogi 3 OS courses + Library (tiered) Custom
Hours of content 2-8h 8+ hours 150+ hours 300+ hours (tiered) Custom
Production source code
Lifetime access
3D AI Accelerator Tracki
Neurones 3D softwarei
Spatial AI job & market inteli
Monthly drop-in sessionsi
Priority support + services accessi ✓ tiered
Custom onboardingi
Team licensing
Price €97 – €497 €297 €1,297 Starts at €1,999 On request

Straight answers

Do I need prior PyTorch experience?

It helps but is not required. The course builds the PyTorch patterns it uses. You do need solid Python and a basic grasp of what training a model means.

What software do I need?

Python, PyTorch, NumPy, and Open3D. All free and open-source. No paid licenses required.

Do I need a GPU?

Training is faster with one, but the datasets are deliberately sized so a CPU works. 16 GB RAM recommended.

How long do I have access?

Lifetime. One payment, permanent access. Every future update is included.

What’s the refund policy?

90 days. Build the model, train it on your own data. If you don’t see results, email me for a full refund.

How is this different from 3D Deep Learning Foundations?

They share the PointNet core, but the framing differs. Foundations (35411) is the broader beginner on-ramp into 3D neural networks. This course is the tighter, engineer-focused implementation track. If you already work in ML and want the architecture itself, this is the direct path.

Is PointNet still relevant in 2026?

As a production model, sometimes. As the foundation of point-based learning, absolutely. PointNet++ and the transformer-based architectures all extend its core ideas. Understanding it from the inside is how you read every paper that came after.

Can I upgrade to an Operating System later?

Yes. When you are ready for the full production stack, contact me for credit toward the 3D Deep Learning OS or the Spatial OS.

Not sure if this course fits?

If you have specific questions about how the curriculum applies to your role, your team’s needs, or your technical background, I’m happy to help you figure it out before you commit.

Book a 15-min call
Course fit and advisory questions only

Stop importing models. Start designing them.

The gap between an engineer who uses 3D models and one who designs them is exactly one course away.

Start Building Now

90-day results guarantee. No questions asked.

Scroll to Top