🔍 Detect and track blue cubes with Intel RealSense D435 using a modular computer vision pipeline for advanced color and ML-based object detection.
🌐 Explore 3D computer vision with Open3D and RealSense for point cloud processing, plane detection, and real-time object detection.
🖼️ Enhance 3D computer vision with this modular toolkit for depth reconstruction, visual odometry, and real-time stereo vision solutions.
This project performs Structure from Motion (SfM) and Iterative Closest Point (ICP) alignment on a series of images to generate and merge point clouds.
Interactive 3D mesh visualization and real-time rendering for Video-Depth-Anything depth maps
A visualisation engine for particle simulations
3D camera design policy document
Deep Learning-Powered 3D City Reconstruction from Satellite Imagery
Three workflows based on aerial imagery or LiDAR point clouds to evaluate the surface available on rooftops by detecting objects.
A research-purposed, GUI-powered, Python-based framework that allows easy development of dynamic point-cloud (and accompanying image) data processing pipelines.
This repository is the culmination of my exploration into advanced 3D computer vision. I built an integrated pipeline capable of transforming 2D images into 3D worlds through depth reconstruction, visual odometry, and comprehensive point cloud processing.
A foundational dive into 3D vision, this project served as my hands-on introduction to processing point clouds with Open3D. I focused on core skills like plane detection, segmentation, and understanding 3D transformations from the ground up.
This project traces my evolution in object detection. I started with classic color-based segmentation, advanced to integrating a YOLOv8 model, and finally incorporated 3D point cloud processing to create a full detection and tracking pipeline.
Python package for point cloud registration using probabilistic model (Coherent Point Drift, GMMReg, SVR, GMMTree, FilterReg, Bayesian CPD)
This is a C++ Uni Bonn course project for SoSe 25, which demonstrates the creation of a 3D occupancy grid map from a series of LiDAR scans taken from the 3D LiDAR sensor - Hesai XT-32, mounted on a ClearPath Husky robotic platform. It leverages modern C++17 features, the Eigen library for linear algebra ops and the Open3D library for visualisation
Addon to import different photogrammetry formats into Blender
Add a description, image, and links to the open3d topic page so that developers can more easily learn about it.
To associate your repository with the open3d topic, visit your repo's landing page and select "manage topics."