Matia Pizzoli
Computer Vision Engineer at Meta
Zürich Metropolitan Area Switzerland
Summary
👤
Senior🎓
Top SchoolMatia Pizzoli is a Computer Vision Engineer with a PhD and a decade of experience translating 3D vision research into real-world systems, currently at Meta in the Zürich area. His work spans multi-camera calibration, stereo and monocular depth estimation, visual-inertial pose estimation and dense reconstruction for applications from AR/VR to UAV navigation. He co-founded Zurich Eye and has a strong track record of turning academic innovations—wearable gaze trackers, VSLAM pipelines and mobile 3D scanning—into products and prototypes. An active contributor to open-source research code, he implemented core REMODE components (camera models, image handling and depth initialization) and is working on denoising improvements, highlighting both algorithmic depth and engineering rigor. Colleagues value his ability to bridge theoretical models and production-quality implementations across CPU/GPU and mobile platforms.
10 years of coding experience
5 years of employment as a software developer
Liceo ScientificoDoctor of Philosophy (PhD) Computer Engineering, Doctor of Philosophy (PhD) Computer Engineering at Sapienza Università di Roma
Italian, English, German
Github Skills (6)
cuda10
depth-estimation10
computer-vision10
c-language10
cprogramming-language10
image-processing9
Programming languages (2)
Github contributions (5)
uzh-rpg/rpg_open_remode
Aug 2015 - Dec 2015
This repository contains an implementation of REMODE (REgularized MOnocular Depth Estimation), as described in the paper.
Role in this project:
Back-end Developer & ML Engineer
Back-end Developer & ML EngineerContributions:188 commits, 9 PRs, 88 pushes in 4 months
Contributions summary:Matia's commits primarily involve implementing and integrating a PinholeCamera class within the codebase, suggesting contributions to the core computer vision components. They introduced an Image struct and templated PaddedMemory, enhancing image handling capabilities. They also implemented the setReferenceImage and update methods, implying they worked on the core functionality for depth map initialization and refinement, which align with the project's focus on regularized monocular depth estimation. Additionally, they are working on a denoiser implementation.
pytorchmonocular-depth-estimationdeep-learningdepthestimation
zurich-eye/gtsam_catkin
Feb 2016 - May 2016
Contributions:6 PRs, 5 pushes, 5 branches in 2 months
gtsampythoncatkin
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.