Mohamed Sayed
Senior Research Scientist at Niantic Spatial, Inc.
London, England, United Kingdom
Summary
🤩
Rockstar🎓
Top SchoolMohamed Sayed is a Senior Research Scientist based in London with a decade of experience at the intersection of computer vision and machine learning, holding a PhD from UCL. He has driven research-to-production work at Niantic on 3D reconstruction, depth estimation, novel view synthesis and generative models, contributing to ECCV-accepted projects and patent-pending depth work. His open-source contributions include engineering and dataset tooling for the influential SimpleRecon repository, where he improved data pipelines, visualization and depth-map handling for large-scale 3D reconstruction. Prior roles span research internships (Disney, Niantic), UCL teaching, and embedded software internships, reflecting a rare blend of academic rigor and production engineering. Known for turning complex vision algorithms into robust code and datasets, he combines strong systems pragmatism with a publication-oriented research mindset.
10 years of coding experience
2 years of employment as a software developer
Bachelors in Electrical Engineering, Computer Engineering, Distinction with honors, Bachelors in Electrical Engineering, Computer Engineering, Distinction with honors at Cairo UniversityUniversity College London
English, Arabic
Github Skills (9)
data-loading10
pytorch10
computer-vision10
python10
data-engineering10
visualizations9
visualization9
pytorch-lightning8
machine-learning8
Programming languages (5)
Github contributions (5)
nianticlabs/simplerecon
Sep 2022 - Jan 2023
[ECCV 2022] SimpleRecon: 3D Reconstruction Without 3D Convolutions
Role in this project:
ML Engineer
ML EngineerContributions:74 commits, 5 PRs, 69 pushes in 4 months
Contributions summary:Mohamed primarily contributed to the codebase by modifying various Python scripts related to data processing, dataset creation, and model visualization within the context of 3D reconstruction. They updated scripts for generating training and testing data tuples, modifying the dataset classes (colmap, vdr, scannet), and adapting visualization tools. Several commits involved bug fixes and refactoring related to depth map handling, data loading, and model parameters.
pytorchscannetreconstructionconvolutionseccv
nianticlabs/nianticlabs.github.io
Jul 2022 - Dec 2022
Contributions:36 commits, 5 PRs, 107 pushes in 4 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.