3D Data Science with Python: Building Accurate Digital Environments with 3D Point Cloud Workflows

by Florent Poux

Our physical world is grounded in three dimensions. To create technology that can reason about and interact with it, our data must be 3D too. This practical guide offers data scientists, engineers, and researchers a hands-on approach to working with 3D data using Python. From 3D reconstruction to 3D deep learning techniques, you'll learn how to extract valuable insights from massive datasets, including point clouds, voxels, 3D CAD models, meshes, images, and more.

Dr. Florent Poux helps you leverage the potential of cutting-edge algorithms and spatial AI models to develop production-ready systems with a focus on automation. You'll get the 3D data science knowledge and code



Understand core concepts and representations of 3D dataLoad, manipulate, analyze, and visualize 3D data using powerful Python librariesApply advanced AI algorithms for 3D pattern recognition (supervised and unsupervised)Use 3D reconstruction techniques to generate 3D datasetsImplement automated 3D modeling and generative AI workflowsExplore practical applications in areas like computer vision/graphics, geospatial intelligence, scientific computing, robotics, and autonomous drivingBuild accurate digital environments that spatial AI solutions can leverageFlorent Poux is an esteemed authority in the field of 3D data science who teaches and conducts research for top European universities. He's also head professor at the 3D Geodata Academy and innovation director for French Tech 120 companies.

1118 pages, Kindle Edition

Published April 9, 2025

Reviews

[Joshua Reuben · Rating 4 out of 5]

Pros: highly informative guide to the world of 3D Data Science !
- essential software & tools for 3D
- 3D data preperation
- 3D reconstruction methods
- 3D data representations
- point cloud conversions with meshes, voxels
- 3D data structures: k-d tree, octree, BVH
- point cloud feature extraction: planarity, linearity, omnivariance, verticality, normals
- 3D shape recognition with RANSAC + region growing, BPA (ball pivoting algorithm)
- photogrammetry, lidar data, depth estimation, 3D construction from multiple images
- Clustering with Multi-RANSAC + DBSCAN
- Unsupervised Segementation with SAM (segment anything)
- introduction to PointTransformers

The core lib is Open3D (unsure how it compares to PCL), but many other python libs are used as well

Cons:
- Chapter 18 on latest deep learning approaches could have been expanded in more depth -more details on text/2D to mesh/point-cloud generation, gaussian splatting. perhaps in volume 2
- no examples of NURBS patch control points from point clouds

Overall, a very informative read that opens up worlds in this more esoteric area of data science !