Martin Rünz
Research Scientist Manager at Synthesia
Munich, Bavaria, Germany
Summary
👤
Senior🎓
Top SchoolMartin Rünz is a research scientist manager based in Munich with 11 years of experience building photorealistic 3D avatars and production-ready computer vision systems at Synthesia. He progressed from Research Scientist to Research Scientist Manager, combining hands-on modelling and systems work with leadership across R&D teams. His PhD from UCL and high-distinction degrees underpin deep expertise in 3D reconstruction, image processing and machine learning, honed further during work with Facebook Reality Labs. An active open-source contributor, he has improved core tools like Pangolin (OpenEXR and Python bindings) and enhanced MaskFusion’s build, GUI and segmentation robustness—skills that bridge research prototypes and deployable pipelines. Colleagues know him for shipping both algorithmic innovations and practical engineering fixes that make complex 3D workflows production-ready.
11 years of coding experience
5 years of employment as a software developer
University of GeorgiaMaster's degree, Computer Science, high distinction (1.1), Master's degree, Computer Science, high distinction (1.1) at University of Koblenz and LandauUniversity College London
English, German, French
Github Skills (13)
video-processing10
configuration-management10
python-bindings10
c-language10
front-end-development10
openexr10
opengl10
cprogramming-language10
python10
image-processing10
numpy9
glsl9
computer-vision8
Programming languages (11)
Github contributions (5)
martinruenz/maskfusion
Oct 2018 - Mar 2020
MaskFusion: Real-Time Recognition, Tracking and Reconstruction of Multiple Moving Objects
Role in this project:
Full-stack Developer
Full-stack DeveloperContributions:22 commits, 4 PRs, 12 pushes in 1 year 5 months
Contributions summary:Martin contributed to the project by making improvements to the build process, including the addition of color support and fixing build script issues. They also enhanced the GUI by enabling the control of parameters via a configuration file. Furthermore, the user addressed a bug related to model identification within the segmentation process and added features to control new model pixel sizes. Finally, they introduced a toml config file for customization.
reconstructiondeep-learningrecognitioncomputer-visiontracking
stevenlovegrove/Pangolin
Oct 2018 - Feb 2020
Pangolin is a lightweight portable rapid development library for managing OpenGL display / interaction and abstracting video input.
Role in this project:Full-stack Developer
Full-stack DeveloperContributions:19 commits, 16 PRs, 4 comments in 1 year 4 months
Contributions summary:Martin significantly contributed to the Pangolin library by implementing features and improvements across different areas. They added support for OpenEXR file formats and python bindings, demonstrating expertise in image processing and cross-language integration. Furthermore, the user updated documentation and implemented features related to video processing, including pythonic video iterations, showcasing their work with tools. The commits indicate a strong understanding of the library's architecture and its intended use.
opengl
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.