🌐 Explore 3D computer vision with Open3D and RealSense for point cloud processing, plane detection, and real-time object detection.

Code developed for "An autonomous floor clearing strategy to tidy up unknown home environments with a mobile manipulator robot" paper and Master's thesis by Letícia dos Santos under the supervision of Jim Torresen, Mariana Kolberg, and Renan Maffei.

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.

Unity video based AR app.

Source code for "Eigen-factors a bilevel optimization for plane SLAM of 3D point clouds"

A high-performance implementation of 3D RANSAC (Random Sample Consensus) algorithm using PyTorch and CUDA.

3D reconstruction from stereo images using epipolar geometry.

Computer Vision

[CVPR 2024] AirPlanes: Accurate Plane Estimation via 3D-Consistent Embeddings

PlaneFill: Fast Normal Map Generation and Plane Detection from Depth Images

Parallel RANSAC for plane detection for multiple point clouds using Python and CUDA

An object detection framework to detect planes in aerial images

A python tool for fitting primitives 3D shapes in point clouds using RANSAC algorithm

experiments with terrain

Semester project for my 3D Computer Geometry & Vision course.

A pipeline to implement surface merge using region growing technique

Point Cloud Library Tutorial with ROS

A collection of dockers for plane detection methods for RGBD data

Plane detection with CGAL region growing algorithm

Programming with classes some planes with altitude and latitude