Automate 3D Scene Understanding
Turn raw point clouds into structured intelligence. Geometric features, scene graphs, mesh extraction, and text/image-to-3D generation. 5 hands-on lessons.
See feature extraction in action
From unstructured 3D points to semantic features, scene graphs, and clean mesh outputs.
Urban, indoor, industrial. The feature pipeline adapts to whatever LiDAR or photogrammetry data you throw at it.
Students trained worldwide across 80 countries.
Production experience distilled into structured, repeatable workflows.
You have points. You need meaning.
Raw 3D data is a bag of XYZ coordinates. It has no semantics. No objects. No relationships. Your downstream application (whether it is a digital twin, a BIM model, or a spatial AI agent) needs structured features that describe what is in the scene and how things relate.
The gap is not running one algorithm. It is orchestrating a feature pipeline: PCA for shape descriptors, Random Forests for classification, graph construction for relationships, and generative models for the parts you cannot capture. That is what turns a scan into a product.
Features are the layer that connects raw 3D data to every downstream application. ML models consume features. Scene graphs are built from features. BIM automation depends on features. Master feature extraction and you hold the key to every 3D AI system. This course builds that layer.
What you’ll build
Five feature extraction techniques wired into one end-to-end pipeline.
PCA + Random Forests
Compute eigenvalue-based features with PCA, then classify with Random Forests. The classic ML pipeline that still beats deep learning on small datasets.
Scene graph generation
Build scene graphs from segmented point clouds. Encode spatial relationships. Query your 3D data like a knowledge base.
Marching cubes meshing
Convert voxel grids and scalar fields into clean triangle meshes with marching cubes. Watertight, decimation-ready output.
Text/image-to-3D
Generate 3D assets from text prompts or images using generative AI. Fill gaps in your captured data when the client needs assets you could not scan.
Production integration
Wire every technique into a single pipeline. Feature API, scene graph export, and downstream ML integration.
Evaluation metrics
Quantify feature quality. Classification accuracy, graph consistency, mesh watertightness. Know when to trust your pipeline.
Feature extraction is the layer I have spent the most time iterating on across 12 years of production projects. Every technique in this course comes from a real project where picking the right feature saved weeks of downstream work, or picking the wrong one cost us a contract.
How this course works
Compact, hands-on, and production-focused.
100% asynchronous
Access everything 24/7 on the LMS. Self-paced. Finish in a weekend.
Code-along projects
Complete Python source code and real point cloud datasets. Clone, run, integrate into your pipelines.
Real datasets
Urban LiDAR, indoor scans, industrial captures. Real noise, real scale, real class imbalance.
Production patterns
Memory-efficient code, batch processing, clean APIs. Ready to drop into your existing stack.
Lifetime access
One payment, permanent access. Every update included.
Upgrade path
This module is part of the Segmentor OS. Your purchase applies as credit if you upgrade later.
This is a focused, single-topic course on feature extraction. If you want the complete segmentation stack (supervised deep learning, algorithmic forge, unsupervised segmentation, labelling, deployed app), consider the Segmentor OS instead. Your purchase applies as credit if you upgrade.
The Curriculum
5 lessons. From geometric features to generative 3D, wired into one pipeline.
Prerequisites
This course requires basic Python and point cloud familiarity.
- Python (mid-level): comfortable with classes, NumPy, virtual environments
- Hardware: 16 GB RAM recommended. GPU helpful for generative 3D but not required
- Basic 3D concepts: understanding of point clouds, voxels, and meshes helpful
No prior feature extraction or graph theory experience required.
Compute eigenvalue-based features with PCA. Train a Random Forest classifier. Still the gold standard for small-data 3D classification.
Turn segmented point clouds into scene graphs. Encode spatial relationships. Enable querying and reasoning.
Convert voxel grids and scalar fields into triangle meshes with marching cubes. The bridge from voxel features to clean surfaces.
Text/image-to-3D with generative models. Fill gaps in captured data with synthesized assets. Wire every method into one end-to-end pipeline.
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.
What students say
Engineers and researchers working with 3D data.
“Our team processed 200M points for a highway survey. Before this course, we were stuck at 10M with crashes. The memory management module saved us weeks of work.”
“I’m a surveyor with 20 years of field experience. This gave me the Python and AI skills to modernize our entire workflow. Best investment I’ve made in my career.”
“RANSAC plus DBSCAN on a 120M-point mining dataset — segmented, volumetric change detected, and report ready in one afternoon. That used to take a week.”
“This course is the foundation I wish I had when I started with LiDAR. The feature extraction module alone reshaped how I approach every project.”
“I trained my first production segmenter on industrial scans within a week. The labelling and class-imbalance modules saved me from rebuilding the dataset twice.”
“The region-growing plus learned-feature pipeline cut our manual classification work in half on a 600M-point urban dataset. We finally retired the spreadsheet.”
“What I needed was someone showing me how to evaluate a segmenter, not just train one. The metrics module is the part most courses skip and the part that matters.”
“I came in fluent in Python but lost on 3D. After Module 2 I was reading PointNet++ papers like a normal human. The intuition Florent builds is the missing link.”
“We replaced a brittle classical pipeline with a sparse-conv network thanks to this course. Production accuracy jumped from 78 to 94 percent on the same data.”
“The training loop debugging chapter was worth the price by itself. I now know why my models stop learning instead of guessing at hyperparameters.”
Get lifetime access
One payment. Every lesson, every update, every line of code.
3D Feature Extraction
Complete feature extraction module + source code + real datasets + lifetime updates
- 5 hands-on lessons (7+ hours)i
- Complete Python source code + datasets
- PCA + Random Forests pipeline
- Scene graph generation
- Marching cubes meshing
- Lifetime access + all future updatesi
- 90-day results guaranteei
Zero-risk guarantee: If you don’t see real results within 90 days, full refund. No questions.
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
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.
Every pipeline was battle-tested on Fortune 500 projects processing billions of points. You’re getting the real playbook, not theory.
Methods validated by peer-reviewed publications, the ISPRS scientific community, and 1,500+ academic citations. Not guesswork.
Built by someone who surveyed in the field, defended a PhD, advised funded startups, and shipped products to Fortune 500 clients.
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 | 3D Feature Extraction | Course Library | 3D AI Architecti | Enterprise |
|---|---|---|---|---|---|
| Courses included | 1 topic | 5 lessons | Full catalogi | 3 OS courses + Library (tiered) | Custom |
| Hours of content | 2-8h | 7+ 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 | €197 | €1,297 | Starts at €1,999 | On request |
Straight answers
Do I need prior ML experience?
Basic familiarity with classification helps, but I explain PCA and Random Forests from the ground up. If you have used scikit-learn once, you are ready.
What hardware do I need?
Minimum 16 GB RAM. A GPU speeds up the generative 3D module but is not required. Everything else runs on CPU.
How is this different from just using Open3D feature functions?
Open3D gives you individual functions. This course teaches you to orchestrate them into a pipeline, integrate with ML, build scene graphs on top, and ship production code.
Can I upgrade to the Segmentor OS later?
Yes. Your purchase applies as credit toward the Segmentor OS. Email me when you are ready.
How long do I have access?
Lifetime. One payment, permanent access. Every future update included.
What’s the refund policy?
90 days. Apply the material. If you are not satisfied, email me for a full refund.
Will scene graphs work on my custom domain?
Yes, once you adapt the relationship rules to your domain. The course shows you how to encode new relationships and extend the graph schema.
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