Get the latest verified insights in 3D Geodata, Point Clouds and Artificial Intelligence. Welcome

👏 curated courses, content, data, code, research paper, 3D interactive experiences and more… 👏

>> (NEW) Advanced 3D Formations at the GeoData Academy <<

Your host: Florent Poux

Florent Poux bridges high-level research & knowledge transmission as an adjunct professor in 3D Geodata (University of Liege), a mentor in Data Sciences & Machine Learning (OpenClassrooms) as well as a 3D creator (3D Geodata Academy). He holds an award-winning Ph.D. in Sciences, and an Engineering MS.c. from the CNAM. He has been at the forefront of automation in Reality Capture for more than 8 years and is a researcher decorated by the ISPRS Jack Dangermond 2019 award.

During his young academic and scientific career, he has given dozens of tech talks, served on the scientific & program committee of several international conferences, and assisted as an editor & reviewer for leading international GIS and Automation journals.

His activities aim at transmitting knowledge and solving automation problematics, through various forms of communication and developments. Florent Poux relies on his expertise and a close group of skilled collaborators that share a vision of global cooperation toward the advancement of technological science for a better society.

Latest articles

• 
  How to automate LiDAR point cloud sub-sampling with PythonNovember 22, 2020
  In this article, I will give you my two favourite 3D processes for quickly structuring and sub-sampling point cloud data with python. You will also be able to automate, export, visualize and integrate results into your favourite 3D software, without any coding experience. I will focus on code optimization while… Read More »How to automate LiDAR point cloud sub-sampling with Python
• 
  Fundamentals to clustering high-dimensional data (3D point clouds)August 9, 2020
  Why unsupervised segmentation & clustering is the “bulk of AI”? What to look for when using them? How to evaluate performances?Well, Clustering algorithms allow data to be partitioned into subgroups, or clusters, in an unsupervised manner. Intuitively, these segments group similar observations together. Clustering algorithms are therefore highly dependent on… Read More »Fundamentals to clustering high-dimensional data (3D point clouds)
• 
  Free LiDAR datasets for self-driving cars AI applicationsMay 25, 2020
  Scale AI releases a new open-source dataset for both academic and commercial use, and accelerate the growth of Autonomous Driving research. For self-driving car applications, we most often avoid explicitly programming machine learning algorithms on how to make decisions, but instead we feed deep learning (DL) models with labeled data… Read More »Free LiDAR datasets for self-driving cars AI applications
• 
  How to represent 3D Data?May 11, 2020
  A visual guide to help choose data representations among 3D point clouds, meshes, parametric models, depth-maps, RGB-D, multi-view images, voxels… The 3D datasets in our computerized ecosystem — of which an increasing number comes directly from reality capture devices — are found in different forms that vary in both the… Read More »How to represent 3D Data?
• 
  5-Step Guide to generate 3D meshes from point clouds with PythonApril 21, 2020
  In this article, I will give you my 3D surface reconstruction process for quickly creating a mesh from point clouds with python. You will be able to export, visualize and integrate results into your favorite 3D software, without any coding experience. Additionally, I will provide you with a simple way… Read More »5-Step Guide to generate 3D meshes from point clouds with Python
• 
  The Future of 3D Point Clouds: a new perspectiveApril 8, 2020
  Discrete spatial datasets known as point clouds often lay the groundwork for decision-making applications. But can they become the next big thing? I am a big point cloud enthusiast. I first discovered their existence 10 years ago, and since then, I have been tweaking my practices through the evolution of… Read More »The Future of 3D Point Clouds: a new perspective

Point Cloud Lab Structure

The different projects are linked to industrial, research or academic purposes. The aim is to provide a visibility and feedback continuum from the emergence of ideas to the implementation of real-world problem-solving.