My team

Latest works (2020):
NEWS:

2020:
- April - This page is no longer maintained. I migrated my site HERE.
- March - We have been awarded a research grant, by the University of Bologna, to develop our Guided Stereo Matching technology!
- February - 2 papers accepted to CVPR 2020!
- February - We will run a tutorial at ECCV 2020 with Konstantinos Batsos and Philippos Mordohai!
- February - We will run a tutorial at CVPR 2020 with Clément Godard, Jamie Watson, Michael Firman, Gabriel J. Brostow!
- January - One paper accepted to ICRA 2020, in collaboration with Univrses!
- January - One paper accepted to CVIU.

2019:
- November - One paper accepted to AAAI 2020!
- October - I'm giving an invited talk at CMP Prague. Thanks to Jiri Matas for this great opportunity!
- September - Two papers accepted to IEEE TPAMI and IEEE Sensors.
- July - Our paper in collaboration with Univrses has been accepted to 3DV 2019!
- June - We will run our tutorial at CVPR! Info and schedules are available here.
- May - I was acknowledged as Outstanding Reviewer and Emergency Reviewer at CVPR 2019!
- March - Alessio and I will talk about "Real-time self-adaptive deep stereo" and "Real-time monocular depth estimation without GPU" at BMVA meeting!
- February - 3 papers (1 oral!) accepted to CVPR 2019!
- January - We got 1 DATE paper accepted!
2018:
- December - I will run a PhD course, "Learning-based dense depth estimation from stereo and monocular images", in January
- November - It's my great pleasure to serve as reviewer for CVPR 2019!
- September - We got 1 IROS, 1 ECCV, 1 3DV and 1 ACCV papers accepted!
- August - I received an honorable mention at CVPL 2018 for presenting my PhD Thesis "Machine learning techniques applied to stereo vision".
- July - I will run a full-day tutorial at 3DV 2018, info and schedules here. This is a joint work with Fabio, Konstantinos Batsos, Philippos Mordohai and Stefano.
- April - I was acknowledged as Outstanding Reviewer at CVPR 2018!
- April - I defended my PhD thesis "Machine learning techniques applied to stereo vision". Thanks to Torsten Sattler and Philippos Mordohai for their reviews and precious comments!
- March - I am part of the program commitee of the 14th IEEE Embedded Vision Workshop (EVW 2018), held in conjunction with CVPR 2018!
2017:
- November - It's my great pleasure to serve as reviewer for CVPR 2018!
- August - In the last 5 months I've been a visiting PhD student at CVG Lab, ETH Zurich. Thanks to Torsten Sattler, Andreas Geiger and Marc Pollefeys for hosting me!
- July - 1 CVPR, 1 BMVC and 2 ICCV (1 spotlight) papers accepted this year!
- July - I gave a talk at MPI in Tübingen, Germany, about my research activities (here the presentation). Thanks to Andreas Geiger and Yiyi Liao for this great opportunity!
2016:
- September - One BMVC and two 3DV papers accepted this year!

Short bio

I received my Bachelor degree in 2012 ("Porting di software e sviluppo di una interfaccia grafica multipiattaforma per telecamera stereo real-time", advisor: Prof. Giovanni Neri, summa cum laude), my Master degree in 2014 ("Improvements to a fast algorithm for accurate stereo matching", advisor: Prof. Stefano Mattoccia, summa cum laude) and my PhD in 2018 ("Machine learning techniques for stereo vision", Supervisor: Prof. Stefano Mattoccia) at Alma Mater Studiorum, University of Bologna. In 2014, I had an internship at Aquifi, Palo Alto (CA), under the supervision of Prof. Roberto Manduchi. In 2017, I was a visiting PhD student at CVG Lab, ETH Zurich, under the supervision of Dr. Torsten Sattler and Prof. Andreas Geiger. I regularly serve as a reviewer for top-tier conferences (CVPR, ICCV, etc.)
Currently, I'm a Post-Doc at Department of Computer Science and Engineering (DISI) and tutor of Calcolatori Elettronici T (laurea triennale in Ingegneria Informatica, Bologna).

Research interests

3D sensing and applications, embedded vision, machine learning, deep learning

Acknowledgements

• Outstanding reviewer (CVPR 2019)
• Emergency reviewer (CVPR 2019)
• Outstanding reviewer (CVPR 2018)
• Honorable mention for PhD thesis presentation (CVPL 2018)

Experience as reviewer

• IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (Outstanding Reviewer 2018, 2019)
• IEEE International Conference on Computer Vision (ICCV)
• IEEE International Conference on Robotics and Automation (ICRA)
• IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
• Asian Conference on Computer Vision (ACCV)
• IEEE Embedded Vision Workshop (EVW)
• IEEE Transaction on Pattern Analysis and Machine Intelligence (TPAMI)
• International Journal of Computer Vision (IJCV)
• Computer Vision and Image Understanding (CVIU)
• IET Intelligent Transport System
• Journal of Signal Processing Systems
• Journal of Optical Society of America (JOSA)
• Journal on Image and Video Processing (JIVP)

Talks, demos and tutorials:

• Inv. Talk: "On the synergies between machine learning and stereo", at the 45th Pattern Recognition and Computer Vision Colloquium, Autumn 2019, Prague, Czech Republic.
• Tutorial: "Learning-based depth estimation from stereo and monocular images: successes, limitations and future challenges", CVPR 2019, Long Beach, California, US.
• Demo: "Real-time monocular depth estimation without GPU", CVPR 2019, June, 2019, Long Beach, US.
• Demo: "Real-time self-adaptive deep stereo", CVPR 2019, June, 2019, Long Beach, US.
• Talk: "Real-time monocular depth estimation without GPU", BMVA meeting on High-Performance Computing for Computer Vision, May 2019, London, UK.
• Demo: "Energy-Efficient Monocular Depth Estimation on ARM-based Embedded Platforms", U-boot at DATE 2019, March, 2019, Florence, Italy.
• Tutorial: "Learning-based depth estimation from stereo and monocular images: successes, limitations and future challenges", 3DV 2018, September 8, 2018, Verona, Italy.
• Demo: "Towards Real-time Learning of Monocular Depth Estimation Enabling Multiple View Synthesis on CPU", ECCV 2018, September 10, 2018 Munich, Germany.
• Demo: "Towards real-time monocular and unsupervised depth estimation on CPU", 3DV 2018, September 5-7, 2018, Verona, Italy
• Inv. Talk: "Deep learning for depth estimation", at Univrses, August 20, 2018, Stockholm, Sweden.
• Inv. Talk: "Deep learning for stereo matching and related tasks", at MPI, July 12, 2017, Tübingen, Germany.

Patents

• Depth determination method based on images, self-adaptive neural networks, and relative system (Real-Time Self Adaptive Deep Stereo), pending. (LINK)
• Depth determination method based on images, and relative system (Guided Stereo Matching), pending. (LINK)

Pubblications - Journals

• M. Poggi, F. Tosi, S. Mattoccia, "Learning a confidence measure in the disparity domain from O(1) features", Computer Vision and Image Understanding (CVIU) (PDF)
• A.Tonioni, M. Poggi, S. Mattoccia, L. Di Stefano, "Unsupervised Domain Adaptation for Depth Prediction from Images", IEEE Transaction on Pattern Analysis and Machine Intelligence (TPAMI) (PDF)
• M. Poggi, G. Agresti, F. Tosi, P. Zanuttigh, S. Mattoccia, "Confidence Estimation for ToF and Stereo Sensorsand its Application to Depth Data Fusion", IEEE Sensors (PDF)
Pubblications - Conferences and workshops
• M. Poggi, F. Aleotti, F. Tosi and S. Mattoccia, "On the uncertainty of self-supervised monocular depth estimation", accepted at The IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2020), June 16-18, 2020, Seattle, Washington, US. (PDF) [CODE]
• F. Tosi, F. Aleotti, P. Zama Ramirez, M. Poggi, S. Salti, L. Di Stefano and S. Mattoccia, "Distilled Semantics for Comprehensive Scene Understanding from Videos", accepted at The IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2020), June 16-18, 2020, Seattle, Washington, US. (PDF) [CODE]
• P. L. Dovesi, M. Poggi, L. Andraghetti, M. Martì, H. Kjellstrom, A. Pieropan, S. Mattoccia, "Real-Time Semantic Stereo Matching", accepted at IEEE/RAS International Conference on Robotics and Automation (ICRA 2020), May 31-June 4, 2020, Paris, France. (PDF)
• F. Aleotti, M. Poggi, F. Tosi, S. Mattoccia, "Learning end-to-end scene flow by distilling single tasks knowledge", accepted at the 34th AAAI Conference on Artificial Intelligence, February 7-12, 2020, New York, US. (PDF)
• L. Andraghetti, P. Myriokefalitakis, P. L. Dovesi, B. Luque, M. Poggi, A. Pieropan, S. Mattoccia, "Enhancing self-supervised monocular depth estimation with traditional visual odometry", accepted at 7th International Conference on 3D Vision (3DV 2019), September 16-19, 2019, Quebec City, Canada (PDF)
• M. Poggi, D. Pallotti, F. Tosi, and S. Mattoccia, "Guided Stereo Matching", accepted at The IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2019), June 16-21, 2019, Long Beach, California, US. (PDF) [CODE]
• F. Tosi, F. Aleotti, M. Poggi and S. Mattoccia, "Learning monocular depth estimation infusing traditional stereo knowledge", accepted at The IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2019), June 16-21, 2019, Long Beach, California, US. (PDF) [CODE]
• A. Tonioni, F. Tosi, M. Poggi, S. Mattoccia and L. Di Stefano, "Real-time self-adaptive deep stereo", accepted at The IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2019), June 16-21, 2019, Long Beach, California, US, ORAL. (PDF) [CODE]
• F. Tosi, M. Poggi, S. Mattoccia, "Leveraging confident points for accurate depth refinement on embedded systems", accepted at The IEEE Embedded Vision Workshop (EVW 2019), June 16, 2019, Long Beach, California, US. (PDF)
• V. Peluso, A. Cipolletta, A. Calimera, M. Poggi, F. Tosi and S. Mattoccia, "Enabling Energy-Efficient Unsupervised Monocular Depth Estimation on ARMv7-Based Platforms", accepted at Design, Automation and Testing in Europe (DATE 2019), March 29-29, 2019, Florence, Italy. (PDF)
• P. Zama Ramirez, M. Poggi, F. Tosi, S. Mattoccia, L. Di Stefano, "Geometry meets semantic for semi-supervised monocular depth estimation", accepted at 14th Asian Conference on Computer Vision (ACCV 2018), December 2-6, 2018, Perth, Australia (PDF) [CODE]
• M. Poggi, F. Tosi, S. Mattoccia, "Learning monocular depth estimation with unsupervised trinocular assumptions", accepted at 6th International Conference on 3D Vision (3DV 2018), September 5-8, 2018, Verona, Italy (PDF) [CODE]
• F.Tosi, M. Poggi, A. Benincasa, S. Mattoccia, "Beyond local reasoning for stereo confidence estimation with deep learning", accepted at the 15th European Conference on Computer Vision (ECCV 2018), September 8-14, 2018, Munich, Germany. (PDF) [CODE]
• M. Poggi, F. Aleotti, F. Tosi, S. Mattoccia, "Towards real-time unsupervised monocular depth estimation on CPU", accepted at IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2018), October 1-5, 2018, Madrid, Spain. (PDF) [CODE]
• F. Aleotti, F. Tosi, M. Poggi, S. Mattoccia, "Generative Adversarial Networks for unsupervised monocular depth prediction", accepted at 3D Reconstruction in the Wild 2018 (3DRW2018), in conjunction with (ECCV 2018), Munich, Germany, September 14, 2018 (PDF)
• M. Poggi, F. Tosi, S. Mattoccia, "Quantitative evaluation of confidence measures in a machine learning world", accepted at The IEEE International Conference on Computer Vision (ICCV 2017), October 22-29, 2017, Venezia, Italy SPOTLIGHT (PDF) [CODE]
• A.Tonioni, M. Poggi, S. Mattoccia, L. Di Stefano, "Unsupervised Adaptation for Deep Stereo", accepted at The IEEE International Conference on Computer Vision (ICCV 2017), October 22-29, 2017, Venezia, Italy (PDF) [CODE]
• F. Tosi, M. Poggi, A.Tonioni, L. Di Stefano, S. Mattoccia, "Learning confidence measures in the wild", accepted at The 28th British Machine Vision Conference (BMVC 2017), September 5-7, 2017, London, UK (PDF)
• M. Poggi, F. Tosi, S. Mattoccia, "Efficient confidence measures for embedded stereo", accepted at The 19th International Conference on Image Analysis and Processing (ICIAP 2017), September 11-15, 2017, Catania, Italy (PDF)
• M. Poggi, F. Tosi, S. Mattoccia, "Even More Confident predictions with deep machine-learning", accepted at The IEEE Embedded Vision Workshop (EVW 2017), July 21, 2017, Honolulu, Hawaii, US (PDF)
• M. Poggi, S. Mattoccia, "Learning to predict stereo reliability enforcing local consistency of confidence maps", accepted at The IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017), July 21-26, 2017, Honolulu, Hawaii, US (PDF) [CODE]
• M. Poggi, S. Mattoccia, "Evaluation of variants of the SGM algorithm aimed at implementation on embedded or reconfigurable devices", accepted at 6th International Conference on 3D Imaging (IC3D2016), December 13-14, 2016, Liège, Belgium (PDF)
• M. Boschini, M. Poggi, S. Mattoccia, "Improving the reliability of 3D people tracking system leveraging on deep-learning", accepted at 6th International Conference on 3D Imaging (IC3D2016), December 13-14, 2016, Liège, Belgium (PDF)
• M. Poggi, S. Mattoccia, "Deep Stereo Fusion: combining multiple disparity hypotheses with deep-learning", accepted at 4th International Conference on 3D Vision (3DV 2016), October 25-28, 2016, Stanford, California, USA (PDF) [CODE]
• M. Poggi, S. Mattoccia, "Learning a general-purpose confidence measure based on O(1) features and a smarter aggregation strategy for semi global matching", accepted at 4th International Conference on 3D Vision (3DV 2016), October 25-28, 2016, Stanford, California, USA, ORAL (PDF) [CODE]
• M. Poggi, S. Mattoccia, "Learning from scratch a confidence measure", accepted at 27th British Machine Vision Conference (BMVC 2016), September 19-22, 2016, York, UK (PDF) [CODE]
• M. Poggi, S. Mattoccia, "A wearable mobility aid for the visually Impaired based on embedded 3D vision and deep learning", First IEEE Workshop on ICT Solutions for eHealth (IEEE ICTS4eHealth 2016) in conjunction with the Twenty-First IEEE Symposium on Computers and Communications, June 27-30, 2016, Messina, Italy (PDF)
• M. Poggi, L. Nanni, S. Mattoccia, "Crosswalk recognition through pointcloud processing and deep-learning suited to a wearable mobility aid for the visually impaired", Image-based Smart City Application (ISCA2015), ICIAP Workshops 2015 : 282-289 (PDF)
• S. Mattoccia, M. Poggi, "A passive RGBD sensor for accurate and real-time depth sensing self-contained into an FPGA", 9th ACM/SIGBED International Conference on Distributed Smart Cameras (ICDSC 2015) (PDF)