Learning-based depth estimation from stereo and monocular images: successes, limitations and future challenges

Speakers

Matteo Poggi
Fabio Tosi
Konstantinos Batsos
Philippos Mordohai
Stefano Mattoccia

Short bios

Matteo Poggi received his MS and PhD from the University of Bologna in 2014 and 2018, respectively. 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 for 5 months CVG Lab lead by Professor Marc Pollefeys in 2017, where he worked on deep learning models for stereo 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. His research interests include deep learning for depth sensing and embedded vision.

Fabio Tosi earned his MS degree from the University of Bologna in 2017. Currently he is a PhD student in Computer Science and Engineering at the University of Bologna, working on deep learning for stereo and monocular depth estimation.

Konstantinos Batsos earned his MS from Stevens Institute of Technology in 2011 and returned to pursue his PhD in 2016. His research interests include binocular and multi-view stereo, deep learning and real-time computer vision.

Philippos Mordohai is an associate professor of Computer Science at Stevens Institute of Technology after earning his PhD from the University of Southern California and postdoctoral appointments at the University of North Carolina and the University of Pennsylvania. His research spans 3D reconstruction from images and video, range data analysis, perceptual organization and active vision

Stefano Mattoccia received his MS and PhD from University of Bologna and 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 computer vision, 3D sensing and embedded computer vision.