The craft of turning billions of points into structured knowledge. Filtering, segmentation, clustering, and feature extraction workflows, all with hands-on Python code.
Turn a careless phone video into a labeled, scaled, measurable 3D room with pretrained SAM, CLIP, and DINOv2, and not one training run. A nine-step open-vocabulary 3D semantics pipeline in Python.
Open-Vocabulary 3D Semantics in Python: SAM, CLIP, and DINOv2 (No Training) Read More »
This tutorial teaches you how to develop a Synthetic point cloud generation engine in Python using NumPy and Open3D, enabling the creation of unlimited labeled 3D data for machine learning. By automating the process, you can save time, reduce costs, and generate realistic training datasets without expensive equipment or manual labeling.
Synthetic Point Cloud Generation of Rooms: Complete 3D Python Tutorial Read More »
By Dr. Florent Poux, PhD in 3D geospatial sciences | Author, 3D Data Science with Python (O’Reilly) | Published 28 February 2025 This tutorial dives deep into the Marching Cubes algorithm, a powerful technique for meshing 3D point clouds using Python. We transform a point cloud into a 3D mesh, experiment with various parameters, and […]
3D Mesh from Point Cloud: Python with Marching Cubes Tutorial Read More »
By Dr. Florent Poux, PhD in 3D geospatial sciences | Author, 3D Data Science with Python (O’Reilly) | Published 29 November 2024 Python Tutorial for Euclidean Clustering of 3D Point Clouds with Graph Theory. Fundamental concepts and sequential workflow for unsupervised segmentation. As you are developing the next generation of AI systems, you face a […]
Python Guide for Euclidean Clustering of 3D Point Clouds Read More »
By Dr. Florent Poux, PhD in 3D geospatial sciences | Author, 3D Data Science with Python (O’Reilly) | Published 4 November 2024 Designing a point cloud workflow is a powerful first-hand approach in 3D data projects. This article explores how processing massive point clouds efficiently isn’t about having more computing power. It’s about being more […]
A Quick Dive into Modern Point Cloud Workflow Read More »
By Dr. Florent Poux, PhD in 3D geospatial sciences | Author, 3D Data Science with Python (O’Reilly) | Published 19 July 2024 RANSAC detects spheres and planes in noisy 3D point clouds by repeatedly fitting a candidate model to a random sample of points and keeping the fit that explains the largest number of inliers. […]
3D Shape Detection with RANSAC and Python (Sphere and Plane) Read More »
By Dr. Florent Poux, PhD in 3D geospatial sciences | Author, 3D Data Science with Python (O’Reilly) | Published 10 June 2024 In this tutorial, I provide a detailed walkthrough on how to generate 3D Voxels from Point Clouds using Python. At the end, you will be able to automate the creation of 3D Voxel […]
3D Point Cloud to Voxels: Python Voxelization Tutorial Read More »
By Dr. Florent Poux, PhD in 3D geospatial sciences | Author, 3D Data Science with Python (O’Reilly) | Published 24 January 2024 This tutorial targets 3D Point Cloud Feature Extraction for developing an interactive Python Segmentation App. The goal is to develop an end-to-end system that can abstract complex point clouds with pertinent features. These […]
Point Cloud Feature Extraction: Complete Guide Read More »
By Dr. Florent Poux, PhD in 3D geospatial sciences | Author, 3D Data Science with Python (O’Reilly) | Published 19 January 2024 3D Modelling: Point Cloud to 3D Mesh In this 3D Tutorial, we learn how to create stunning 3D meshes from point clouds using Python and 3D Modelling techniques. We focus on how to […]
3D Modelling: Point Cloud to 3D Mesh Read More »
By Dr. Florent Poux, PhD in 3D geospatial sciences | Author, 3D Data Science with Python (O’Reilly) | Published 5 March 2022 A Story of Point Clouds and Perception Foreword on the 3D conference This 9th International Workshop 3D-ARCH focused on “3D Virtual Reconstruction and Visualization of Complex Architectures”. It started in 2005 in Venice and […]
Point Cloud Processing for geometric and semantic interpretation Read More »
