Seminar by Dr. Tolga BIRDAL from Department of Computing of Imperial College London

Recent advances in 3D vision and geometric deep learning have revolutionized how machines perceive and reconstruct the 3D world. Yet, fundamental challenges remain in shape representations, geometric priors, and topological robustness for learning-based systems. In this talk, Dr. Tolga Birdal will discuss how geometry and topology advance modern 3D vision, drawing from his work on 3D reconstruction, shape correspondence, and geometric deep learning.

Dr. Tolga Birdal is an assistant professor (Lecturer) and a UKRI Future Leaders Fellow in the Department of Computing of Imperial College London. Previously, he was a senior Postdoctoral Research Fellow at Stanford University within the Geometric Computing Group of Prof. Leonidas Guibas. Tolga has defended his masters and Ph.D. theses at the Computer Vision Group under Chair for Computer Aided Medical Procedures, Technical University of Munich led by Prof. Nassir Navab. He was also a Doktorand at Siemens AG under supervision of Dr. Slobodan Ilic working on “Geometric Methods for 3D Reconstruction from Large Point Clouds”. His thesis was awarded the prestigious EMVA Young Professional Award. His current foci of interest involve topological / geometric machine learning and 3D computer vision. More theoretical work is aimed at investigating and interrogating limits in geometric computing and non-Euclidean inference as well as principles of deep learning. Tolga has several publications at the well-respected venues such as NeurIPS, CVPR, ICCV, ECCV, ICLR, T-PAMI, ICRA, IROS, ICASSP and 3DV. He is the AC for CVPR, ICCV, ECCV and is currently program-chairing 3DV 2025. Aside from his academic life, Tolga has co-founded multiple companies including Befunky, a widely used web-based image editing platform.