- This event has passed.
Fall 2022 GRASP Seminar: Tomas Pajdla, Czech Technical University, “Solving Minimal Problems in the Age of Machine Learning”
October 10, 2022 @ 3:00 pm - 4:00 pm
This was a hybrid event with in-person attendance in Levine 307 and virtual attendance…
ABSTRACT
I will discuss several our recent advances in understanding minimal problems in computer vision using numerical algebraic geometry tools, i.e., Homotopy continuation and monodromy, as well as machine learning. I will talk about our classification of minimal problems under full and partial visibility and about learning startups for solving hard minimal problems by local methods.
Presenter
Tomas Pajdla
Tomas an associate professor and distinguished researcher at the CIIRC – Czech Institute of Informatics, Robotics and Cybernetics of the Czech Technical University in Prague. He works in geometry and algebra of computer vision and robotics, with emphasis on camera geometry, 3D reconstruction, and industrial vision. He contributed to introducing epipolar geometry of panoramic cameras, generalized camera models generated by linear mappings, generalized epipolar geometries, and to developing solvers for minimal problems in structure from motion.