Guillaume Bourmaud is an Associate Professor at Bordeaux INP with deep expertise in computer vision, signal processing, and machine learning. He holds a PhD from the University of Bordeaux and previously worked as a Computer Vision Researcher at Toshiba, focusing on robust optimization and 3D reconstruction.
He has contributed to numerous academic publications, including recent papers for CVPR 2025, exploring topics like image matching, feature learning, and camera pose estimation. His work advances how complex visual data is processed and understood.
Unique fact: His research explores hallucinating visual correspondence, essentially teaching machines to reason about parts of a scene that are hidden or out of view.