Fabio Tosi, PhD

Currently, I am a postdoctoral researcher at the Department of Computer Science and Engineering (DISI) at the University of Bologna, and I also serve as an Adjunct Professor for the Fundamentals of Computer Science course at the Department of Electrical, Electronic, and Information Engineering “Guglielmo Marconi”. My research interests are in computer vision and machine learning, with a particular focus on 3D reconstruction from images.

In 2021, I received my PhD degree from the University of Bologna under the supervision of Professor Stefano Mattoccia. Previously, I received a Master’s and Bachelor’s degree in Computer Engineering in 2017 and 2014, respectively.

In 2020, I was a visiting PhD student in the research group of the Autonomous Vision Group (AVG) of Professor Andreas Geiger at the Max Planck Institute for Intelligent Systems and the University of Tübingen.

In 2022, I was awarded the best PhD thesis by the Italian Association for Research in Computer Vision, Pattern Recognition and Machine Learning (CVPL).

You can download my full Curriculum Vitae here! (16/03/2023)


  • 05/2023 It is with great pleasure that I announce my achievement as an Outstanding Reviewer at CVPR 2023!
  • 02/2023 Our paper NeRF-Supervised Deep Stereo has been accepted at CVPR 2023!
  • 02/2023 I received my National Scientific Habilitation (09/H1)
  • 11/2022 Best PhD Thesis Award, Italian Association for Computer Vision Research (CVPL 2022)
  • 02/2022 2 papers accepted at 3DV 2022.
  • 02/2022 2 papers accepted at CVPR 2022 this year!
  • 11/2021 Proof of Concept d’Ateneo, PoC UNIBO 3rd edition (Principal Investigator, PI)
  • 09/2021 Best Paper Honorable Mention to our work “Neural Disparity Refinement for Arbitrary Resolution Stereo"

My Research Team

Stefano Mattoccia

Matteo Poggi


Full publication list on Google Scholar
*indicates joint first authorship

NeRF-Supervised Deep Stereo - NEW!
Fabio Tosi, Alessio Tonioni, Daniele De Gregorio, Matteo Poggi
Conference on Computer Vision and Pattern Recognition (CVPR), 2023
project page | paper | supplementary | code

Monovit: Self-supervised monocular depth estimation with a vision transformer
Chaoqiang Zhao, Youmin Zhang, Matteo Poggi, Fabio Tosi,, Xianda Guo, Zheng Zhu, Guan Huang, Yang Tang, Stefano Mattoccia
International Conference on 3D Vision (3DV), 2022
paper | code

On the Synergies Between Machine Learning and Binocular Stereo for Depth Estimation From Images: A Survey
Matteo Poggi, Fabio Tosi, Konstantinos Batsos, Philippos Mordohai, Stefano Mattoccia
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021

SMD-Nets: Stereo Mixture Density Networks
Fabio Tosi, Yiyi Liao, Carolin Schmitt, Andreas Geiger
Conference on Computer Vision and Pattern Recognition (CVPR), 2021
paper | supplement | blog | code | video | poster

Learning monocular depth estimation infusing traditional stereo knowledge
Fabio Tosi, Filippo Aleotti, Matteo Poggi, Stefano Mattoccia
Conference on Computer Vision and Pattern Recognition (CVPR), 2019
paper | | supplementary | code | poster | video

Real-time self-adaptive deep stereo


Alessio Tonioni, Fabio Tosi, Matteo Poggi, Stefano Mattoccia
Conference on Computer Vision and Pattern Recognition (CVPR), 2019
paper | supplementary | code | video | live demo

Guided Stereo Matching
Matteo Poggi*, Davide Pallotti*, Fabio Tosi, Stefano Mattoccia
Conference on Computer Vision and Pattern Recognition (CVPR), 2019
paper | demo code | video | poster

Reversing the cycle: self-supervised deep stereo through enhanced monocular distillation
Filippo Aleotti*, Fabio Tosi*, Li Zhang, Matteo Poggi, , Stefano Mattoccia
European Conference on Computer Vision (ECCV), 2020
paper | code | video