3D Vision & Deep Learning
3D Deep Learning OS
From your first ANN to a deployed 3D AI app. 7 production modules. Every architecture that matters: PointNet, PointNet++, KPConv, GrowSP. No black boxes.
Note from Florent
This is the production stack I wish someone had handed me when I started with 3D deep learning. No toy datasets, no shortcuts. You’ll train, evaluate, and deploy real models.
What you will build
Module 01
Foundations
A structured orientation to 3D deep learning. Data types, workflows, and the first setup.
Module 02
Neural network engineering
Build every core architecture from scratch. ANN, CNN, ResNet, EfficientNet.
Module 03
3D data engineering for DL
The 3D-specific data layer. Voxel datasets, PyTorch Dataset classes, and preprocessing.
Module 04
Point-based architectures
The PointNet family end to end. PointNet and PointNet++: fundamentals, data prep, training.
Module 05
Advanced architectures
The production-grade architectures. 3D CNN, 3D R-CNN, KPConv, and GrowSP.
Module 06
Generative, hybrid, LLMs
The frontier of 3D AI. Generative models, hybrid systems, and LLMs for 3D.
Module 07
Production deployment
Ship. Workflow and system design for production. Step-by-step 3D Python app deployment.
Your starting resources
Additional guides and code packs unlock as you progress through each module.
