Pascal Fua

Professor Pascal Fua is a distinguished faculty member at EPFL (Swiss Federal Institute of Technology) in the School of Computer and Communication Science. He joined EPFL in 1996 and currently serves as Head of the Computer Vision Laboratory (CVLAB). His extensive research spans multiple cutting-edge areas in computer vision and geometric deep learning, with applications ranging from 3D reconstruction to medical imaging and aerodynamic optimization.

Dr. Fua's research interests encompass Computer Vision, 3D Reconstruction, Shape Modeling, Geometric Deep Learning, Medical Image Analysis, Augmented Reality, Motion Recovery, Surface Mesh Processing, and Aerodynamic Shape Optimization. His work demonstrates a remarkable ability to bridge theoretical computer vision with practical applications across diverse domains. His research has evolved from traditional geometric computer vision techniques to incorporating deep learning approaches for 3D modeling, with recent focus on differentiable rendering, implicit surface representations, and applications in medical imaging and engineering design.

His publication record shows a consistent trajectory of high-impact research, with recent work focusing on differentiable iso-surface extraction, geometric deep learning for aerodynamic shape optimization, and novel approaches to 3D reconstruction. His work spans both theoretical advances in computer vision algorithms and practical applications in medical imaging, autonomous driving, and computational fluid dynamics.

• IEEE Fellow
• Multiple ERC Grants recipient
• Associate Editor of IEEE Transactions for Pattern Analysis and Machine Intelligence

Throughout his career, Professor Fua has mentored numerous PhD students who have gone on to make significant contributions in computer vision and related fields. His laboratory has established collaborations across multiple disciplines, including medical imaging, aerospace engineering, and neuroscience, demonstrating the broad applicability of his research. His current work continues to push the boundaries of geometric deep learning and 3D vision, with particular emphasis on making these techniques more practical and applicable to real-world engineering and medical problems.