Bridging the Gap Between Computational Photography and Visual Recognition:
UG2 Prize Challenge
$75K in Prizes
CVPR 2018 Workshop Challenge
June 18, 2018


What is the current state-of-the art for image restoration and enhancement applied to images acquired under less than ideal circumstances?

Can the application of enhancement algorithms as a pre-processing step improve image interpretability for manual analysis or automatic visual recognition to classify scene content?

The UG2 Challenge seeks to answer these important questions for general applications related to computational photography and scene understanding. As a well-defined case study, the challenge aims to advance the analysis of images collected by small UAVs by improving image restoration and enhancement algorithm performance using the UG2 Dataset




Awarded in prizes

Available Challenges

Image Enhancement to Facilitate Manual Inspection

Evaluation of the qualitative enhancement of images from the UG2 dataset.

  • Psychophysics-based evaluation will be deployed, whereby a reasonably large number of raters will determine which image, the original or the restored/enhanced version, is of higher quality.
  • Rater reaction time will be used to gauge the difficulty of presented image pair.
  • Image Enhancement to Improve Automatic Object Recognition

    Evaluation of the quantitative enhancement of images from the UG2 dataset.

  • Improvement on top-1 and top-5 classification of enhanced images will determine whether the enhancement techniques improve recognition.
  • Keynote speakers

    Speaker Photo

    Dr. Taylor's research interests lie primarily in the fields of Computer Vision and Robotics and include: reconstruction of 3D models from images, vision-guided robot navigation and smart camera networks.

    Camillo J. Taylor
    University of Pennsylvania
    Speaker Photo

    Dr. Hoogs supervises the Kitware Computer Vision group and provides strategic direction in this area.

    Anthony Hoogs
    Senior Director of Computer Vision, Kitware
    Speaker Photo

    Dr. Boehnen is a Senior Program Manager at the Intelligence Advanced Research Projects Activity (IARPA), Office of the Director of National Intelligence.

    Christopher Boehnen
    Senior Program Manager, IARPA

    Important Dates

    Open registration

    January 31 - April 1, 2018

    Submission deadline

    April 15, 2018

    Winners announcement

    May 15, 2018

    CVPR Workshop

    June 18, 2018


    Speaker Photo

    Dr. Scheirer's research is primarily focused around the problem of recognition, including the representations and algorithms supporting solutions to it.

    Walter J. Scheirer
    University of Notre Dame
    Speaker Photo

    Graduate Student

    Sreya Banerjee
    University of Notre Dame
    Speaker Photo

    Graduate Student

    Rosaura G. VidalMata
    University of Notre Dame
    About the Challenge

    Support for this challenge workshop is provided under IARPA contract #2016-16070500002. This workshop is supported in part by the Office of the Director of National Intelligence (ODNI), Intelligence Advanced Research Projects Activity (IARPA). The views and conclusions contained herein are those of the organizers and should not be interpreted as necessarily representing the official policies, either expressed or implied, of ODNI, IARPA, or the U.S. Government. The U.S. Government is authorized to reproduce and distribute reprints for governmental purposes notwithstanding any copyright annotation therein.