ICCV Daily 2021 - Friday

learning approaches and when one has an advantage over the other. Finally, David Suter from Edith Cowan University will speak more generally about what can be exploited from traditional vision and what cannot be exploited once we simply rely on deep learning without assuming anything else as knowledge. Federica and Matteo invite anyone who is interested in this unique event to join them for an afternoon of fascinating talks, spotlight sessions, and insightful discussions. Prior to their current roles, Federica was a postdoc researcher at the Czech Technical University in Prague, and Matteo was a postdoc researcher at the University of Bologna. Federica has a PhD in Industrial and Information Engineering, while Matteo has a PhD in Computer Science and Engineering. They are joined on the organizing team of TradiCV by Andrea Fusiello from the University of Udine, Stefano Mattoccia from the University of Bologna, Adrien Bartoli from the Université Clermont Auvergne, and Torsten Sattler and Tomas Pajdla from the Czech Technical University in Prague. The 1st Workshop on Traditional Computer Vision in the Age of Deep Learning (TradiCV) will be held on Saturday afternoon. 19 DAILY ICCV Friday Comparison between 3D reconstructions by a deep network and the method proposed in: Finite Aperture Stereo: 3D Reconstruction of Macro-Scale Scenes Traditional Computer Vision in the Age of Deep Learning