Invited Speakers

Richard Hartley is an Emeritus Professor at the Australian National University. He is a Fellow of the Australian Academy of Science and the Royal Society. He is renowned as one of the founders of the field of multi-view geometry in computer vision and an author of the textbook on the topic (Hartley & Zisserman, Multiple View Geometry in Computer Vision) with over 34k citations. Besides his extensive work on classical approaches to calibration and pose estimation, he also investigates learning-based approaches.

Webpage: https://comp.anu.edu.au/people/richard-hartley/

Gabriela Csurka is a Principal Scientist at NAVER LABS Europe, France. Her main research interests are image and 3D understanding, visual localization, domain adaptation, and visual language models. She has a strong expertise in learning scene representations that facilitate accurate camera pose estimation in the context of visual localization. Gabriela is also working on foundation models for 3D computer vision tasks, as well as their application in localization (pose estimation) and 3D reconstruction. 

Webpage: https://europe.naverlabs.com/people_user_naverlabs/Gabriela-Csurka/

Eric Brachmann is a senior staff scientist at Niantic. He is an expert on learning-based camera pose estimation. His pioneering work on using differentiable RANSAC for learning-based scene coordinate regression was one of the first papers that combined classical RANSAC-based pose estimation with machine learning. He later extended this approach to guide RANSAC-based estimation process. One overarching theme of his work is robust and efficient camera pose estimation.

Webpage: https://ebrach.github.io/

Fredrik Kahl is a professor at Chalmers University of Technology in Gothenburg, Sweden. His research interest cover a wide range of topics, including learning local features, visual localization, robust estimation and optimization, multiple-view geometry, and geometric deep learning. Fredrik has done pioneering work on critical motions for self-calibration, robust estimation, and optimization in the context of multiple-view geometry. Fredrik has extensive knowledge about classical approaches for calibration and pose estimation.

Webpage: https://fredkahl.github.io/