I received a PhD in Computer Science and Engineering from the University of Bologna in 2002 and currently I'm Associate Professor at the Department of Computer Science and Engineering, School of Engineering and Architecture, University of Bologna. My research interests include: computer vision, deep-learning, depth and scene flow estimation from monocular and stereo images, domain adaptation, and embedded computer vision. I regularly serve as reviewer for major international conferences and journals [CV]

 

Short bio

Stefano Mattoccia

Associate Professor

Department of Computer Science and Engineering (DISI)
School of Engineering and Architecture
University of Bologna


Address: Viale del Risorgimento, 2  40136 Bologna, Italy

Phone:   +39 051 2093860  - Fax +29 051 2093869 

Email:     stefano.mattoccia#AT#unibo.it

Research

Keywords: computer vision, machine-learning, 3D vision, depth and scene flow estimation from monocular and stereo images, domain adaptation, embedded computer vision

My research activity is concerned with computer vision, machine learning applied to computer vision problems and embedded vision systems. For a more detailed overview take a look at the publication page or Google Scholar


My team: Matteo Poggi (Post-doc), Fabio Tosi (PhD student) and Filippo Aleotti (PhD student)

   
   

 
  1. -Sono disponbili tesi di laurea (magistrale e triennale) e tirocini nell’ambito di tematiche inerenti la computer vision con particolare riferimento alla generazione e alla elaborazione di dati 3D mediante machine learning.
    Le tematiche di ricerca vertono su: deep-learning/machine learning, computer vision e 3D vision, sistemi di computer vision embedded, sistemi assistivi per ipovedenti e non vedenti, robotica, sistemi di guida autonoma.

  2. -Sono disponibili tesi e tirocini da svolgere all’estero e/o in azienda

  3. -Per informazioni o per fissare un appuntamento: stefano.mattoccia__AT__unibo.it

  4. -Una lista di tesi e tirocini svolti e in corso è disponibile a questo link

Tesi di laurea e tirocini/Theses and internships

  1. -72943 Sistemi Digitali M, Ing. Informatica (Magistrale) 2019-2020

  2. -28012 Calcolatori Elettronici T, Ing. Informatica  2009-2019

  3. -88146 Fondamenti di Informatica P2, Ing. Meccatronica  2019

  4. -78101 Sistemi Embedded riconfigurabili M, Ing. Informatica (Magistrale) 2009-2019

  5. -28011 Reti Logiche T, Ing. Informatica 2016-2018, Ing. Automazione 2006-2008, Ing. Elettronica 2003-2005

Courses

Service and professional activities

  1. -Best paper award at 14th IEEE Embedded Vision Workshop (CVPR 2018)

  2. -Best demo paper award at 4th IEEE Mobile Vision Workshop (CVPR2014)

  3. -Outstanding reviewer, International Conference on Computer Vision and Pattern Recognition (CVPR 2013)

  4. -Best paper award at 7th IEEE Embedded Vision Workshop (CVPR 2011)

Awards

Recent talks, tutorials, courses, seminars and demos

Informativa sulla privacy disponibile a questo link

Updates:

  1. -2 papers accepted at CVPR 2020

  2. -Tutorial at ECCV 2020: Facing depth estimation in the wild with deep networks

  3. -Tutorial at CVPR 2020: Learning and understanding single image depth estimation in the wild

  4. -1 paper accepted at ICRA 2020

  5. -1 CVIU paper

  6. -1 paper accepted at AAAI-20

  7. -1 IEEE TPAMI paper

  8. -1 IEEE Sensors paper

  9. -New patent (pending): Depth determination method based on images, and relative system

  10. -We welcome Li Zhang and Shen Yuan, visiting PhD students from China

  11. -3 papers accepted at CVPR 2019: 1 oral and 2 poster

  12. -Tutorial at CVPR 2019: Learning-based depth estimation from stereo and monocular images

  13. -Two demos at CVPR 2019: real-time self-adaptive deep-stereo and real-time monocular depth estimation


Recent selected papers:
- Learning end-to-end scene flow by distilling single tasks knowledge, AAAI 2020

  1. -Unsupervised Domain Adaptation for Depth Prediction from Images, TPAMI

  2. -Enhancing self-supervised monocular depth estimation with traditional visual odometry, 3DV 2019

  3. -Real-time self-adaptive deep stereo, CVPR 2019 (Oral)

  4. -Guided stereo matching, CVPR 2019

- Learning monocular depth estimation infusing traditional stereo knowledge, CVPR 2019
- Geometry meets semantic for semi-supervised monocular depth estimation, ACCV 2018

- Learning monocular depth estimation with unsupervised trinocular assumptions, 3DV 2018

- Beyond local reasoning for stereo confidence estimation with deep learning, ECCV 2018
- Towards real-time unsupervised monocular depth estimation on CPU, IROS 2018

- Quantitative evaluation of confidence measures in a machine learning world, ICCV 2017

- Unsupervised Adaptation for Deep Stereo, ICCV 2017

  1. -Learning to predict stereo reliability enforcing local consistency of confidence maps, CVPR 2017

Updates and recent results

  1. -General co-Chair 12th IEEE Embedded Vision Workshop (EVW2016), CVPR 2016 workshop

  2. -Program Chair 11th IEEE Embedded Vision Workshop (EVW2015), CVPR 2015 workshop

  3. -Program co-Chair 10th IEEE Embedded Vision Workshop (EVW2014), CVPR 2014 workshop

  4. -Area Chair IEEE International Conference on Multimedia & Expo ICME 2014

  5. -Area Chair IEEE International Conference on Multimedia & Expo ICME 2013

  6. -Guest Editor IEEE Journal of Selected Topics in Signal Processing, Special Issue on Emerging Techniques in 3D 2013

  7. -Guest Editor Springer’s Journal of Signal Processing Systems 2016

  8. -Reviewer for major international conferences and the following journals:

    IEEE Transactions on Pattern Analysis and Machine Intelligence, IEEE Transactions on Image Processing, IEEE Transactions on Medical Images, IEEE Transactions on Circuits and Systems I, IEEE Transactions on Circuits and Systems - II, IEEE Transactions on Circuits and Systems for Video Technology, IEEE Transactions on VLSI Systems, IEEE  Transactions on Neural Systems and Rehabilitation Engineering, IEEE Transactions on Emerging Topics in Computing, IEEE Signal Processing Letter, Computer Vision and Image Understanding, Image and Vision Computing, Machine Vision and Applications, Pattern Recognition Letters, Elsevier Journal of Visual Communication and Image Representation, Journal of Signal Processing Systems, Journal of Microprocessors and Microsystems, Digital Signal Processing, IET Computer Vision, IET Intelligent Transport Systems, VLSI Design, EURASIP Journal on Image and Video Processing, ISRN Machine Vision, SPIE Journal of Electronic Imaging, SPIE Optical Engineering, Optics Express, International Journal of Computational Vision and Robotics, Artificial Intelligence in Medicine, International Journal of Artificial Intelligence and Soft Computing, Artificial Intelligence Review, The Knowledge Engineering Review, Journal of Network and Computer Applications

  9. -Key member (2010-2014) of the Interest Group on 3D Rendering, Processing and Communications of  IEEE Multimedia Communication TC

  10. -Member of IEEE and CVPL (IAPR) 

  11. -Member of the following PhD dissertation committees:

        TU Graz (2018), University of Bologna (2018), University of Torino (2018), University of Padova (2017),
        University of Parma (2015)

  Filippo Aleotti, University of Bologna (2018-present)
      Unsupervised monocular depth estimation

  Fabio Tosi, University of Bologna (2017-present)
      Deep-learning for 3D reconstruction

      Matteo Poggi, University of Bologna (2014-2017)
      Machine learning for stereo vision

  Leonardo De-Maeztu Reinares, Public University of Navarre, Pamplona, Spain (2009-2012)
      Towards accurate and real-time local stereo correspondence algorithms: computational efficiency and massively
      parallel architectures
, Co-supervised with Arantxa Villanueva (Public University of Navarre)

  Federico Tombari, University of Bologna (2006-2009)
      Methodologies for visual correspondence, Co-supervised with Prof. Luigi Di Stefano (University of Bologna)

PhD students

  1. -Course: Depth sensing technologies for autonomous vehicles, S. Mattoccia, Poggi, F. Tosi, F. Aleotti, Master in Sustainable and Integrated Mobility in Urban Regions, University of Bologna, Imola (Bologna), Oct/Nov 2019

  2. -Tutorial: Learning-based depth estimation from stereo and monocular images: successes, limitations and future challenges, M. Poggi, F. Tosi, K. Batsos, P. Mordohai, S. Mattoccia, CVPR 2019, Long Beach, USA, June 17, 2019

  3. -Demo: Real-time monocular depth estimation without GPU, M. Poggi, F. Tosi, F. Aleotti, S. Mattoccia, CVPR 2019, Long Beach, USA, June 18-20, 2019

  4. -Demo: Real-time self-adaptive deep stereo, A. Tonioni, F. Tosi, M. Poggi, S. Mattoccia. L. Di Stefano, CVPR 2019, Long Beach, USA, June 18-20, 2019

  5. -Course: Computer vision and machine learning,  EMBA | Bologna Business School, Bologna, May 17 2019

  6. -Demo: Energy-Efficient Monocular Depth Estimation on ARM-based Embedded Platforms, V. Peluso, A. Cipolletta, A. Calimera,  M. Poggi, F. Tosi, S. Mattoccia, U-booth at DATE 2019, March, 2019, Florence, Italy

  7. -Talk: Real-time depth from image with deep-learning, EON Experience Fest 2019, March 28, 2019, Bologna [PDF]

  8. -Course for PhD students: Learning-based dense depth estimation from stereo and monocular images, Matteo Poggi and Stefano Mattoccia, January/February 2019 [Abstract] [Website

  9. -Talk: Learning-based methods for depth from images and confidence estimation, Naver Labs Europe, Grenoble (France), December 14, 2018 [PDF]

  10. -Tutorial: Learning-based depth estimation from stereo and monocular images: successes, limitations and future challenges, M. Poggi, F. Tosi, K. Batsos, P. Mordohai, S. Mattoccia 3DV 2018, Verona, Italy, Sept. 8, 2018 - Slides available here.

  11. -Demo:Towards Real-time Learning of Monocular Depth Estimation Enabling Multiple View Synthesis on CPU, M. Poggi, F. Tosi, S. Mattoccia European Conference on Computer Vision (ECCV2018), Sept. 10, 2018 Munich, Germany

  12. -Talk: 3D Sensing from Images, with Matteo Poggi and Fabio Tosi, European Machine Vision Forum 2018, Bologna, Italy, September 6, 2018 [Abstract] [PDF]

  13. -Demo: Towards real-time monocular and unsupervised depth estimation on CPU, wM. Poggi, F. Aleotti and F. Tosi, International Conference on 3D Vision (3DV2018), Sept. 5-7, 2018, Verona, Italy

  14. -Talk: Deep-learning for depth estimation, TU Graz, Graz University of Technology - Institute of Computer Graphics & Vision, April 17, 2018

  15. -Talks: Deep-learning for low level vision problems and Mapping of computer vision algorithms on FPGAs with High Level Synthesis tools, Summer School on Deep Learning on Chip (Macloc2017) September 20-22, 2017 – Politecnico di Torino, Torino (Italy) [PDF]

Real-time monocular depth estimation with PyD-Net (see IROS 2018 paper) on iOS and Android devices: code available