Mathis Petrovich
Research Scientist, Simulation Technology
Zurich, Zurich, Switzerland
Summary
🤩
Rockstar🎓
Top SchoolMathis Petrovich is a research scientist at NVIDIA’s Spatial Intelligence Lab with nine years of research experience at the intersection of 3D human motion, computer vision, and optimal transport. He completed PhD work across École des Ponts and Max Planck Institute, and has held research positions at RIKEN, DxO and Carnegie Mellon, translating mathematical tools like local linear models and optimal transport into practical vision and simulation systems. At NVIDIA he moved from an internship to a simulation-focused scientist role, applying academic rigor to large-scale simulation and spatial intelligence problems. Based in Zurich, he blends strong theoretical foundations in mathematics with hands-on implementation experience, making him adept at turning complex models for human motion and occlusion handling into production-ready research. An affinity for bridging deep learning with principled transport methods is a recurring, distinctive thread in his work.
9 years of coding experience
Master's degree, Computer Science, Master's degree, Computer Science at École normale supérieure Paris-SaclayBachelor's degree, Computer Science, Bachelor's degree, Computer Science at Université Paris CitéDoctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at École des Ponts ParisTechMPSI/MP*, Mathematics and Computer Science, MPSI/MP*, Mathematics and Computer Science at Lycée Masséna
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (28)
text-analysis10
textual10
driver10
gnu8
userspace8
linux8
pytorch8
foreground7
3d7
python7
unity3d5
linear-regression5
regularization5
animation5
image-processing4
Programming languages (4)
Github contributions (5)
Mathux/Fall
Feb 2020 - Apr 2021
Fast local linear regression with anchor regularization
Contributions:11 commits, 1 PR, 6 pushes in 1 year 1 month
linear-regressionregularization
Mathux/TEMOS
May 2022 - Nov 2022
Official PyTorch implementation of the paper "TEMOS: Generating diverse human motions from textual descriptions", ECCV 2022 (Oral)
Contributions:57 commits, 42 pushes, 1 branch in 6 months
pytorchtextualhuman-motionmotion-generation
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.