Episode 2: 3D Object Detection (Part 1)
3D AI Live/Replay/Episode 02
Teach a network to label every point of a 3D scene.
We prepare a labelled point cloud, train a KPConv model on it, and write its predictions back into a file any point cloud software can read.
The brief
What we build in this session
You start with
Point cloud files with colour, and their semantic labels.
You end with
A LAS file with a classification field on every point.
How we get there
Data preparation, KPConv training, then export of the predictions to LAS.
The replay
Watch the full session
The materials
Everything you need to follow along
The code
KPConv and data preparation (Google Drive)
Open →The dataset
Train and test sets (Google Drive)
Open →Go deeper
The papers and tools behind the session
- KPConv, the paper→
- Hugues Thomas, Ph.D. thesis on point cloud semantic segmentation→
- PyTorch, getting started with CUDA→
- CUDA Toolkit→
Where you are
You are in the free part of the academy
Four levels, each one a step deeper than the one before. Take them in your own order.
The live sessions
Free replays, open to everyone. This page is one of them.
The weekly tutorials
One hands-on 3D tutorial a week, free to read.
3The book
3D Data Science with Python: the full method, chapter by chapter.
4The programme
The 3D AI Architect: from 3D scan to deliverable, automated, with me beside you.
The next session is live, and your seat is free.
Save your seat once. You get every session, your personal link, the reminders and the replay.
