Label a 3D point cloud with any word you type. This complete guide walks the open-vocabulary 3D segmentation stack in Python: pretrained SAM cuts the scene, CLIP scores each region, and a scene graph lets an LLM answer questions about the space.
Open-Vocabulary 3D Segmentation Complete Guide Read More »
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 »
A complete Python pipeline for 3D point cloud labeling from phone photos using interactive painting, pinhole projection, and KD-tree fusion — no GPU required.
3D Point Cloud Labeling from Photos with Python (and why AI can’t design it for you) Read More »
By Dr. Florent Poux, PhD in 3D geospatial sciences | Author, 3D Data Science with Python (O’Reilly) | Published 8 December 2024 We dive into SuperPoint Transformer, a novel approach for 3D semantic segmentation presented in the research paper “Efficient 3D Semantic Segmentation with Superpoint Transformer“. We also explore the core concepts, examine the research […]
Tutorial for 3D Semantic Segmentation with Superpoint Transformer Read More »
By Dr. Florent Poux, PhD in 3D geospatial sciences | Author, 3D Data Science with Python (O’Reilly) | Published 30 September 2022 Julia Tutorial for 3D Data Science Discover the make-it-all alternative to Python, Matlab, R, Perl, Ruby, and C through a 6-step workflow for 3D point cloud and mesh processing. If you are always on […]
Julia Tutorial for 3D Data Science Read More »
By Dr. Florent Poux, PhD in 3D geospatial sciences | Author, 3D Data Science with Python (O’Reilly) | Published 14 May 2021 Learn 3D point cloud segmentation with Python A complete python tutorial to automate point cloud segmentation and 3D shape detection using multi-order RANSAC and unsupervised clustering (DBSCAN). If you have worked with point […]
Learn 3D point cloud segmentation with Python Read More »
By Dr. Florent Poux, PhD in 3D geospatial sciences | Author, 3D Data Science with Python (O’Reilly) | Published 16 February 2021 Visualise Massive point cloud in Python. Point clouds past the 10 million point mark are too dense for classical visualisation libraries such as Matplotlib, so this tutorial uses PPTK, which relies on an […]
Visualise Massive point cloud in Python Read More »
By Dr. Florent Poux, PhD in 3D geospatial sciences | Author, 3D Data Science with Python (O’Reilly) | Published 9 December 2020 Scale AI released a new LiDAR point cloud dataset, and accelerate the growth of Autonomous Driving research. Point Cloud Data labelling Data labelling, also called data annotation/tagging/classification, is the process of tagging (i.e. […]
Free LiDAR point cloud for self-driving cars Read More »
