Summary
Vincent Leroy is a team leader and researcher specializing in geometric deep learning and 3D computer vision, currently heading the GEODE team at NAVER LABS Europe. He combines a strong academic foundation—PhD work at Inria on large-scale multi-camera 4D reconstruction with publications at ICCV and ECCV—with hands-on R&D experience building reconstruction and perception systems for autonomous driving, robotics, and human pose estimation. Vincent’s work spans camera pose estimation, calibration, and monocular/multiview depth, and he has shipped a full software stack from his PhD contributions for multi-camera reconstruction. Based in Grenoble, he blends algorithmic rigor with practical system-building, moving ideas from conference papers into deployed research prototypes. Less obvious: his background in physics and electronics gives him an edge in sensor-aware engineering and cross-disciplinary problem solving. He is known for turning dense multi-view data into robust geometric representations that drive applied perception systems.
2 years of coding experience
6 years of employment as a software developer
CPE Lyon
French, English, German