Learning and understanding single image depth estimation in the wild

Organizers

Matteo Poggi

He received his PhD from University of Bologna in 2018. Since 2014 his research focuses on stereo matching and deep learning. He was an intern at Aquifi in Palo Alto in 2014, supervised by Prof. Roberto Manduchi, and visited CVG Lab led by Professor Marc Pollefeys in 2017 supervised by Dr. Torsten Sattler and Prof. Andreas Geiger. Currently he is a post-doc at the Department of Computer Science and Engineering of University of Bologna. Since 2018 he regularly serves as reviewer for major computer vision conferences and journals, being acknowledged as outstanding reviewer at CVPR 2018 and 2019.

Fabio Tosi

He earned his MS degree in computer science engineering from the University of Bologna in 2017. Currently he is a third-year PhD student in Computer Science and Engineering at the University of Bologna, working on deep learning for stereo and monocular depth estimation. Since 2019 he regularly serves as reviewer for major computer vision conferences and journals.

Filippo Aleotti

He received his MS degree computer science engineering from the University of Bologna in 2018. Currently he is enrolled in second year PhD program in Structural and Environmental Health Monitoring and Management (SEHM2) at the Department of Computer Science and Engineering of University of Bologna, where he conducts research in deep learning for depth sensing.

Stefano Mattoccia

He received his PhD in Computer Science Engineering from the University of Bologna in 2002. Currently, he is an associate professor at the Department of Computer Science and Engineering of the University of Bologna. His research activity is mainly focused on 3D sensing from images, deep-learning and embedded computer vision. He has been co-guest editor for a special issue of IEEE Journal of Selected Topics in Signal Processing on emerging techniques in 3D in 2013, area chair at ICME 2013 and 2014 for the 3D track, Co-Program Chair for the Embedded Vision Workshop 2014, Program Chair for Embedded Vision Workshop 2015 and lead guest editor for a special issue of Springer’s Journal of Signal Processing Systems on Embedded Computer Vision.

Clément Godard

He obtained his PhD in 2018 under the supervision of Dr. Gabriel Brostow at University College London. His research focused on 3D reconstruction and deep learning. After a couple of internships in Seattle at both Google and Facebook, he realized that the weather was decidedly better on the other side of the pond and he moved to California where he is a research engineer for Skydio working on embedded deep depth prediction.

Michael Firman

He is a Senior Research Scientist at Niantic, in the Augmented Reality Research and Development Group. He previously co-founded Matrix Mill, which was acquired by Niantic in 2018. He was a postdoc with Lourdes Agapito and Gabriel Brostow and did his PhD with Simon Julier at University College London, working on diverse vision and machine learning projects, ranging from volume-completion to automatic ecological monitoring. He previously completed his MEng in Engineering Design at the University of Bristol.

Jamie Watson

He is a Computer Vision Software Engineer at Niantic, makers of PokemonGO and Harry Potter: Wizards Unite. He works in the Augmented Reality R\&D Group. Currently he is working on problems relating to scene understanding from single RGB images, to improve the realism of AR for millions of users. He received his MSc in Machine Learning from UCL in 2018, before joining Niantic in London. Prior to this, he received his Bachelors in Mathematics from the University of St Andrews.

Gabriel J. Brostow

He is professor of Machine Vision in Computer Science, Chief Research Scientist at Niantic and has worked at University College London for 10 years. He was previously a post-doc with Marc Pollefeys at ETHZ, and a Marshall Sherfield fellow and postdoc at Cambridge University with Roberto Cipolla. He did his PhD with Irfan Essa at Georgia Tech, and his BS in Electrical Engineering at the University of Texas at Austin. He was Program co-Chair for BMVC 2017, Associate Editor for T-PAMI, and will be Program co-Chair for ECCV 2022.