Manuel Antequera
Research Engineer at Meta
Zug, Zug, Switzerland
Summary
🤩
Rockstar🎓
Top SchoolManuel Antequera is a research engineer with 12 years of experience bridging academic AI research and production-grade computer vision systems, currently contributing at Meta from Zug, Switzerland. He holds a PhD in Artificial Intelligence and a strong electronics background, which surfaces in work spanning structure-from-motion, point-cloud mapping, and robotics toolkits. At Mapillary he moved from intern to computer vision engineer, contributing to the open-source OpenSfM pipeline by vectorizing algorithms and fixing orientation and projection bugs that improve large-scale image reconstruction. His contributions to MRPT and pytorch-metric-learning show a pragmatic focus on robustness and maintainability—improving map insertion logic and enabling customizable accuracy metrics and tests. Known for combining low-level numerical care with research rigor, he brings both sensor- and model-level insight to applied vision problems.
12 years of coding experience
7 years of employment as a software developer
Master’s Degree, Artificial Intelligence, Master’s Degree, Artificial Intelligence at Universidad de MálagaDoctor of Philosophy - PhD, Artificial Intelligence, Doctor of Philosophy - PhD, Artificial Intelligence at University of Groningen
Spanish, English
Github Skills (18)
pytorch10
opencv10
robotics10
c-language10
python10
numpy10
computer-vision10
maps10
cprogramming-language10
3d-reconstruction10
testing9
machine-learning9
data-structures8
autonomous-driving8
data-structure8
Programming languages (8)
Github contributions (5)
mapillary/OpenSfM
Jan 2018 - May 2022
Open source Structure-from-Motion pipeline
Role in this project:
Back-end Developer & Computer Vision Engineer
Back-end Developer & Computer Vision EngineerContributions:239 commits, 41 PRs, 156 pushes in 4 years 4 months
Contributions summary:Manuel primarily contributed to the `opensfm/opensfm` repository by implementing vectorized versions of existing functions and adding new functionalities to process data and make the code more efficient. The user introduced `project_many` and `transform_many` functionalities specifically for projective cameras. They also made improvements to the codebase by refactoring to use `tf.angle_between_vectors` for angle calculations and by fixing multiple bugs in the codebase, including corrections related to the orientation of images.
structure-from-motionpythonpipelinemotionintrinsics
MRPT/mrpt
Jan 2014 - Oct 2015
:zap: The Mobile Robot Programming Toolkit (MRPT)
Role in this project:Back-end Developer
Back-end DeveloperContributions:16 commits, 1 PR in 1 year 9 months
Contributions summary:Manuel contributed to the Mobile Robot Programming Toolkit (MRPT) by implementing and modifying functionalities related to point cloud maps. Their work involved adding new insertion options for point maps, specifically related to handling invalid points and horizontal tolerances. Furthermore, they addressed minor issues and made changes to adapt to the latest libraries' features. The user's contributions suggest a focus on improving the map-related data structures and algorithms within the MRPT framework.
robot-programmingroboticsmobile-robotspoint-cloudsrobot-framework
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.