John Smith

Luca Del Pero
PhD, Computer Vision

  • Office: Blippar, London
  • luca dot delpero at blippar dot com
  • Skype Contact: prusso83
  • Download my CV
I am lead research scientist at Blippar, working on Computer Vision and Machine Learning for Augmented Reality. Previously I was a PostDoc researcher in Vittorio Ferrari's CALVIN lab at the University of Edinburgh. I received my Ph.D. in Computer Science at The University of Arizona, under the advisement of Dr. Kobus Barnard. I work in the areas of computer vision and machine learning. My research interests include pose estimation, fine-grained classification, 3D scene understanding from monocular images, articulated motion analysis, city-scale localization, Bayesian modeling and inference methods, and mobile Computer Vision.

RESEARCH

  • Weakly supervised learning from videos

    Our research focuses on weakly supervised learning from unstructured Internet videos. By reasoning about motion, we can discover many different properties of object classes under very little human supervision. These include the recurrent behaviors of the class, its visual aspects, its physical parts, as well as the spatiotemporal alignment between different class instances in different videos (an example is shown on the left)
    Behavior discovery and alignment
    [IJCV 2016] [CVPR 2015] [Webpage] [Dataset]
    Phyisical part discovery
    [CVPR 2016] [Webpage + Dataset] [TechCrunch article]
    Visual aspect discovery
    [IMAVIS 2016]


  • Understanding images of indoor scenes

    Our goal is to jointly understand the geometry and the semantics of indoor scenes, such as bedrooms and kitches. We would like to infer what is where in 3D, by solving the problems of 3D reconstruction and object recognition jointly. Doing this from a single 2D image also involves inferring the parameters of the camera. The image shows a fit for a bedroom, where the red lines denote the inferred room boundaries, the green and the blue box are respectively a correctly identified picture frame and a bed.
    [CVPR 2013 paper] [data]
    [CVPR 2012 paper] [data]
    [CVPR 2011 paper] [data]
    [Dissertation]

  • Image and text alignment

    Image keywords and captions provide information about what is in the image, but we do not know which words correspond to which image elements. Our goal is to align words in the caption with visual features (see the main project page). My focus is on how to use specialized object detectors for improving initial estimates of the alignment, as illustrated in the image on the left (click on it to enlarge).
    [ACM MM 2011 paper]

PUBLICATIONS

Benjamin Risse, Michael Mangan, Luca Del Pero, and Barbara Webb, "Visual Tracking of Small Animals in Cluttered Natural Environments Using a Freely Moving Camera", Workshop on Visual Wildlife Monitoring, ICCV, October, 2017 [pdf]

[bibtex]

Luca Del Pero, Susanna Ricco, Rahul Sukthankar, and Vittorio Ferrari, "Behavior Discovery and Alignment of Articulated Object Classes from Unstructured Video", International Journal of Computer Vision (IJCV), January, 2017 [pdf]

[bibtex]

[webpage]

[dataset]

Luca Del Pero, Susanna Ricco, Rahul Sukthankar, and Vittorio Ferrari, "Discovering the physical parts of an articulated object class from multiple videos", IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), June, 2016 [pdf]

[bibtex]

[webpage and dataset]

[TechCrunch article on this paper]
Anestis Papazoglou, Luca Del Pero, and Vittorio Ferrari, "Video temporal alignment for object viewpoint", Proceedings of the Asian Conference on Computer Vision (ACCV), November, 2016 [pdf]

[bibtex]

[Dataset]

Anestis Papazoglou, Luca Del Pero, and Vittorio Ferrari, "Discovering object aspects from video", Journal of Image Vision and Computing (IMAVIS), April, 2016 [pdf]

[bibtex]

Luca Del Pero, Susanna Ricco, Rahul Sukthankar, and Vittorio Ferrari, "Articulated Motion Discovery Using Pairs of Trajectories", IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), June, 2015 [pdf]

[bibtex]

[webpage]

[dataset]

Ernesto Brau, Jinyan Guan, Kyle Simek, Luca Del Pero, Colin Dawson, Kobus Barnard. "Bayesian 3D tracking from monocular video" International Conference on Computer Vision (ICCV), December, 2013. [pdf] [bibtex]

Luca Del Pero, Joshua Bowdish, Emily L. Hartley, Bonnie Kermgard, Kobus Barnard. "Understanding Bayesian rooms using composite 3D object models" IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), June, 2013. [pdf]

[bibtex]

Luca Del Pero, Kobus Barnard. "Top-down Bayesian inference for indoor scenes", invited book chapter in "Advanced topics in Computer Vision" by Giovanni Maria Farinella, Sebastiano Battiato and Roberto Cipolla, Springer, Advances in Computer Vision and Pattern Recognition Series, 2013. [book chapter]

[bibtex]

Luca Del Pero, Joshua Bowdish, Daniel Fried, Bonnie Kermgard, Emily L. Hartley, Kobus Barnard. "Bayesian geometric modeling of indoor scenes," IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), June, 2012. [pdf]

[bibtex]

Luca Del Pero, Jinyan Guan, Ernesto Brau, Joseph Schlecht, Kobus Barnard. "Sampling Bedrooms," IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2009-2016, June, 2011. [pdf]

[bibtex]

Luca del Pero, James Magahern, Philip Lee, Emily Hartley, Ping Wang, Atul Kanaujia, Niels Haering, and Kobus Barnard, "Fusing object detection and region appearance for image-text alignment," ACM Multimedia short paper, 2011. [pdf]

[bibtex]

WORKSHOPS

Luca Del Pero, Kobus Barnard. "Bayesian inference of indoor scenes using composite 3D object models", Scene Understanding Workshop (Sunw) at IEEE CVPR, June, 2013. [pdf]

Colin Dawson, Luca Del Pero, Clayton Morrison, Mihai Surdaneau, Gustave Hahn-Powell, Zachary Chapman and Kobus Barnard . "Bayesian modeling of scenes and captions", Workshop on Vision and Language (WVL) at NAACL HLT, June, 2013. [slides]

EDUCATION

Aug 2009 - Jul 2013

PhD, Computer Science
University of Arizona
Dissertation: Top-down Bayesian inference and modeling for indoor scenes

Sep 2005 – Feb 2008

Master of Science, Computer Engineering
Politecnico di Torino

Sep 2002 – July 2005

Bachelor of Science, Computer Engineering
Politecnico di Torino

INDUSTRY

Jan 2016 - present

Blippar, London, UK
Computer Vision Research Engineer

  • 3D pose estimation, tracking and deep learning for augmented reality on mobile devices

Oct 2013 - Dec 2015

School of Informatics, University of Edinburgh, Edinburgh, UK
PostDoc Researcher in Vittorio Ferrari's Calvin group

  • Weakly supervised learning from unconstrained Internet videos

Apr 2008 - Aug 2009

GFI Informatique, Sophia Antipolis, France
Software engineer

  • Worked as a consultant at Amadeus on designing and implementing ticketing systems for major airlines.

May 2005 – Dec 2005

E-Mentor, Turin, Italy
Intern

  • Implementation of Voip (Voice over IP) solutions for managing audio streams in a distance learning environment.
Go to Top