Christian Forster
Computer Vision And Machine Learning Engineer at Meta
Zurich, Zurich, Switzerland
Summary
🤩
Rockstar🎓
Top SchoolChristian Forster is a computer vision and machine learning engineer with 13 years of experience building real-time tracking and SLAM systems, currently leading multiple vision efforts at Meta for Quest devices including hand/body tracking, object tracking, room scanning and keyboard tracking. He holds a PhD in Informatics from the University of Zurich and an MSc in Robotics from ETH Zürich, blending deep academic expertise in visual-inertial SLAM and dense reconstruction with product-driven delivery. A founder-turned-operator, he co-founded Zurich Eye (acqui-hired by Facebook) and previously ran high-traffic consumer platforms, demonstrating both entrepreneurial grit and production-scale engineering. His open-source contributions include practical improvements to the well-regarded rpg_svo visual odometry repository, reflecting a focus on dataset benchmarking and robust back-end tooling for vision research.
13 years of coding experience
6 years of employment as a software developer
Doctor of Philosophy (Ph.D.) Informatics, Doctor of Philosophy (Ph.D.) Informatics at University of ZurichMSc Robotics Systems Control, MSc Robotics Systems Control at ETH Zürich
German, English, French
Github Skills (18)
benchmark10
c-language10
testing10
graph10
benchmarking10
factors10
cprogramming-language10
ros10
robotics9
algorithm9
code-optimization9
algorithms9
optimisation9
numerical-optimization9
optimization9
Programming languages (1)
Github contributions (5)
uzh-rpg/rpg_svo
Mar 2014 - Apr 2016
Semi-direct Visual Odometry
Role in this project:
Back-end Developer
Back-end DeveloperContributions:181 commits, 5 PRs, 5 pushes in 2 years 1 month
Contributions summary:Christian's contributions centered on benchmark node functionality within a visual odometry project. Their work involved removing user input and marker visualization from the benchmark node, moving the trace file to a separate function, and adapting dataset naming conventions. Furthermore, they added functionality to set the first frame, essential for synthetic dataset benchmarking. Their work suggests they were actively involved in optimizing and adapting the project for different datasets and evaluation scenarios.
odometrysemidirectvisual-odometry
uzh-rpg/fast_neon
May 2013 - Feb 2016
Contributions:9 commits in 2 years 9 months
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.