Summary
Francis Engelmann is an Assistant Professor and computer vision researcher with 14 years of experience specializing in machine learning and 3D scene understanding. He has driven high-impact academic and industry projects at Stanford, ETH Zürich, Google, Apple, X, and RWTH Aachen, publishing influential work on open-vocabulary 3D instance segmentation and functional 3D scene understanding (NeurIPS, ICLR, CVPR). His recent contributions include OpenMask3D and OpenNeRF at Google and SceneFun3D and OpenFunGraph at ETH, blending pixel-wise feature rendering with semantics and affordances for real-world indoor spaces. Now based in Palo Alto and holding prestigious postdoctoral fellowships, he bridges foundational research with practical systems for multi-object reconstruction and scalable point-cloud learning. Colleagues note his knack for turning complex 3D problems into generalizable, open-set solutions that enable downstream scene reasoning and robotics applications.
14 years of coding experience
10 years of employment as a software developer
Athénée de Luxembourg
Master of Science (M.Sc.), Computer Science, Master of Science (M.Sc.), Computer Science at RWTH Aachen University
ETH AI Center PostDoctoral Fellow, ETH AI Center PostDoctoral Fellow at ETH Zürich
SNSF PostDoc Mobility Fellowship, SNSF PostDoc Mobility Fellowship at Stanford University
English, German, Luxembourgish, French, Spanish